mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-10 16:04:04 +00:00
CosmicClash Training Bot
1620 lines
54 KiB
JSON
1620 lines
54 KiB
JSON
{
|
|
"stage_index": 2,
|
|
"attempt": 3,
|
|
"status": "in_progress",
|
|
"log": [
|
|
{
|
|
"stage_index": 0,
|
|
"stage_number": 4,
|
|
"stage_name": "handling",
|
|
"experiment": "20260816-0858-gen5-s4-handling",
|
|
"attempt": 0,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/airborne_fraction": 0.2285692382156849,
|
|
"rollout/ep_len_mean": 138.9746000366211,
|
|
"rollout/ep_rew_mean": 8.531756190299987,
|
|
"rollout/forward_motion_fraction": 0.28261195290088653,
|
|
"rollout/goal_rate": 0.5371200009584427,
|
|
"rollout/grounded_upright_fraction": 0.47041099911928175,
|
|
"rollout/mean_altitude": 2.5816375048160554,
|
|
"rollout/productive_air_touch_fraction": 0.0,
|
|
"rollout/upright_fraction": 0.7536708096265793,
|
|
"rollout/vertical_thrust_mean": -0.046195002141292206
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.5371 < 0.8000"
|
|
],
|
|
"evaluation_goal_failures": [
|
|
"easy.json: goal_rate=0.710 < 0.800"
|
|
],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-16T14:13:26+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-0858-gen5-s4-handling.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 46,
|
|
"wins_b": 25,
|
|
"draws": 29,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 20,
|
|
"wins_b": 18,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 26,
|
|
"wins_b": 7,
|
|
"draws": 17
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 27,
|
|
"team_1": 44
|
|
},
|
|
"win_rate_a": 0.46
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-16T14:13:26+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-0858-gen5-s4-handling.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 46,
|
|
"wins_b": 25,
|
|
"draws": 29,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 20,
|
|
"wins_b": 18,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 26,
|
|
"wins_b": 7,
|
|
"draws": 17
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 27,
|
|
"team_1": 44
|
|
},
|
|
"win_rate_a": 0.46
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 0,
|
|
"stage_number": 4,
|
|
"stage_name": "handling",
|
|
"experiment": "20260816-1513-gen5-s4-handling-retry1",
|
|
"attempt": 1,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 7.999999821186065e-05,
|
|
"rollout/airborne_fraction": 0.21746457129716873,
|
|
"rollout/ep_len_mean": 119.63403997802735,
|
|
"rollout/ep_rew_mean": 10.153738673210144,
|
|
"rollout/forward_motion_fraction": 0.3045943345427513,
|
|
"rollout/goal_rate": 0.6827200036048889,
|
|
"rollout/grounded_upright_fraction": 0.3728669992983341,
|
|
"rollout/mean_altitude": 2.524057677268982,
|
|
"rollout/productive_air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/upright_fraction": 0.7505921430587769,
|
|
"rollout/vertical_thrust_mean": -0.030821001116302794
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.6827 < 0.8000"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-16T20:26:42+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-1513-gen5-s4-handling-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 58,
|
|
"wins_b": 24,
|
|
"draws": 18,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 25,
|
|
"wins_b": 14,
|
|
"draws": 11
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 33,
|
|
"wins_b": 10,
|
|
"draws": 7
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.58
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-16T20:26:42+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-1513-gen5-s4-handling-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 58,
|
|
"wins_b": 24,
|
|
"draws": 18,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 25,
|
|
"wins_b": 14,
|
|
"draws": 11
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 33,
|
|
"wins_b": 10,
|
|
"draws": 7
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.58
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 0,
|
|
"stage_number": 4,
|
|
"stage_name": "handling",
|
|
"experiment": "20260816-2126-gen5-s4-handling-retry2",
|
|
"attempt": 2,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 9.999999776482581e-05,
|
|
"rollout/airborne_fraction": 0.22292538091540337,
|
|
"rollout/ep_len_mean": 104.10827992248535,
|
|
"rollout/ep_rew_mean": 9.0257121925354,
|
|
"rollout/forward_motion_fraction": 0.31477042868733407,
|
|
"rollout/goal_rate": 0.7731199976205826,
|
|
"rollout/grounded_upright_fraction": 0.3524109998345375,
|
|
"rollout/mean_altitude": 2.5850543739795686,
|
|
"rollout/productive_air_touch_fraction": 7.999999821186065e-05,
|
|
"rollout/upright_fraction": 0.7720990960597992,
|
|
"rollout/vertical_thrust_mean": 0.003765997685031034
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.7731 < 0.8000"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-17T02:36:22+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 65,
|
|
"wins_b": 22,
|
|
"draws": 13,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 30,
|
|
"wins_b": 14,
|
|
"draws": 6
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 35,
|
|
"wins_b": 8,
|
|
"draws": 7
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 49
|
|
},
|
|
"win_rate_a": 0.65
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-17T02:36:22+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/promoted/easy.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 65,
|
|
"wins_b": 22,
|
|
"draws": 13,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 30,
|
|
"wins_b": 14,
|
|
"draws": 6
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 35,
|
|
"wins_b": 8,
|
|
"draws": 7
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 49
|
|
},
|
|
"win_rate_a": 0.65
|
|
}
|
|
],
|
|
"decision": "pass",
|
|
"decision_override": {
|
|
"date": "2026-08-17",
|
|
"original_decision": "fail",
|
|
"original_failures": [
|
|
"rollout/goal_rate=0.7731 < 0.8000"
|
|
],
|
|
"reason": "Human override. Only miss was the training goal-rate floor, at 0.7731 vs 0.80; every evaluation gate passed (65-22-13 vs promoted/easy.json, 87% non-draw, 12.6% physical-side imbalance) and the goal rate improved monotonically across all three attempts (0.537 -> 0.683 -> 0.773). Also promoted to Game/bots/promoted/medium.json on the same evidence. Stage 5 resumes from this checkpoint."
|
|
}
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260819-2307-gen5-s5-intercepts",
|
|
"attempt": 0,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/airborne_fraction": 0.2607660475373268,
|
|
"rollout/ep_len_mean": 110.36292008972168,
|
|
"rollout/ep_rew_mean": 18.444599359512328,
|
|
"rollout/forward_motion_fraction": 0.3145952378213406,
|
|
"rollout/goal_rate": 0.760879998922348,
|
|
"rollout/grounded_upright_fraction": 0.18850000035762787,
|
|
"rollout/mean_altitude": 3.2910697083473206,
|
|
"rollout/productive_air_touch_fraction": 0.0,
|
|
"rollout/upright_fraction": 0.7767313802242279,
|
|
"rollout/vertical_thrust_mean": 0.036809997959644535
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_fraction=0.0000 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-20T10:57:16+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260819-2307-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 49,
|
|
"wins_b": 32,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 24,
|
|
"wins_b": 17,
|
|
"draws": 9
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 25,
|
|
"wins_b": 15,
|
|
"draws": 10
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.49
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-20T10:57:16+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260819-2307-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 49,
|
|
"wins_b": 32,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 24,
|
|
"wins_b": 17,
|
|
"draws": 9
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 25,
|
|
"wins_b": 15,
|
|
"draws": 10
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.49
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260820-1157-gen5-s5-intercepts-retry1",
|
|
"attempt": 1,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/airborne_fraction": 0.26865795205533505,
|
|
"rollout/ep_len_mean": 114.6417999572754,
|
|
"rollout/ep_rew_mean": 22.072290691375734,
|
|
"rollout/forward_motion_fraction": 0.3363774284422398,
|
|
"rollout/goal_rate": 0.7213600025177002,
|
|
"rollout/grounded_upright_fraction": 0.20986333368718624,
|
|
"rollout/mean_altitude": 3.3522593455314635,
|
|
"rollout/productive_air_touch_fraction": 0.0,
|
|
"rollout/upright_fraction": 0.781577188372612,
|
|
"rollout/vertical_thrust_mean": 0.039050997858699414
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.7214 < 0.7500",
|
|
"rollout/productive_air_touch_fraction=0.0000 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-20T23:56:33+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260820-1157-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 52,
|
|
"wins_b": 29,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 23,
|
|
"wins_b": 17,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 12,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 46
|
|
},
|
|
"win_rate_a": 0.52
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-20T23:56:33+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260820-1157-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 52,
|
|
"wins_b": 29,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 23,
|
|
"wins_b": 17,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 12,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 46
|
|
},
|
|
"win_rate_a": 0.52
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260821-0056-gen5-s5-intercepts-retry2",
|
|
"attempt": 2,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/airborne_fraction": 0.2582751900553703,
|
|
"rollout/ep_len_mean": 107.35483990478515,
|
|
"rollout/ep_rew_mean": 21.299435565948485,
|
|
"rollout/forward_motion_fraction": 0.34663380977511404,
|
|
"rollout/goal_rate": 0.7518799985647202,
|
|
"rollout/grounded_upright_fraction": 0.18188000024855136,
|
|
"rollout/mean_altitude": 3.246318883895874,
|
|
"rollout/productive_air_touch_fraction": 0.0,
|
|
"rollout/upright_fraction": 0.7892111427783967,
|
|
"rollout/vertical_thrust_mean": 0.06337799821014051
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_fraction=0.0000 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-21T12:49:28+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260821-0056-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 56,
|
|
"wins_b": 31,
|
|
"draws": 13,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 27,
|
|
"wins_b": 20,
|
|
"draws": 3
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 11,
|
|
"draws": 10
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 49
|
|
},
|
|
"win_rate_a": 0.56
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-21T12:49:28+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260821-0056-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 56,
|
|
"wins_b": 31,
|
|
"draws": 13,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 27,
|
|
"wins_b": 20,
|
|
"draws": 3
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 11,
|
|
"draws": 10
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 49
|
|
},
|
|
"win_rate_a": 0.56
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260822-1242-gen5-s5-intercepts",
|
|
"attempt": 0,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00037999999150633814,
|
|
"rollout/airborne_fraction": 0.3646399522125721,
|
|
"rollout/ep_len_mean": 114.69971998596192,
|
|
"rollout/ep_rew_mean": 28.210284183502196,
|
|
"rollout/forward_motion_fraction": 0.4648521428704262,
|
|
"rollout/goal_rate": 0.7230000025033951,
|
|
"rollout/grounded_upright_fraction": 0.19716999983787536,
|
|
"rollout/mean_altitude": 3.4371472091674806,
|
|
"rollout/productive_air_touch_fraction": 5.9999998658895494e-05,
|
|
"rollout/upright_fraction": 0.7519121896028519,
|
|
"rollout/vertical_thrust_mean": 0.06471899795718491
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.7230 < 0.7500",
|
|
"rollout/productive_air_touch_fraction=0.0001 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-23T01:58:22+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260822-1242-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 54,
|
|
"wins_b": 25,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 25,
|
|
"wins_b": 13,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 12,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 37,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.54
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-23T01:58:22+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260822-1242-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 54,
|
|
"wins_b": 25,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 25,
|
|
"wins_b": 13,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 12,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 37,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.54
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260823-0258-gen5-s5-intercepts-retry1",
|
|
"attempt": 1,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00025999999418854715,
|
|
"rollout/airborne_fraction": 0.3638041906952858,
|
|
"rollout/ep_len_mean": 116.89268002319336,
|
|
"rollout/ep_rew_mean": 26.092227859497072,
|
|
"rollout/forward_motion_fraction": 0.46304495227336884,
|
|
"rollout/goal_rate": 0.7216800025701523,
|
|
"rollout/grounded_upright_fraction": 0.18362999991327525,
|
|
"rollout/mean_altitude": 3.4676120114326476,
|
|
"rollout/productive_air_touch_fraction": 7.999999821186065e-05,
|
|
"rollout/upright_fraction": 0.7491730006933213,
|
|
"rollout/vertical_thrust_mean": 0.052752998621095906
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.7217 < 0.7500",
|
|
"rollout/productive_air_touch_fraction=0.0001 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-23T16:34:58+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260823-0258-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 63,
|
|
"wins_b": 23,
|
|
"draws": 14,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 29,
|
|
"wins_b": 13,
|
|
"draws": 8
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 34,
|
|
"wins_b": 10,
|
|
"draws": 6
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.63
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-23T16:34:58+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260823-0258-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 63,
|
|
"wins_b": 23,
|
|
"draws": 14,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 29,
|
|
"wins_b": 13,
|
|
"draws": 8
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 34,
|
|
"wins_b": 10,
|
|
"draws": 6
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.63
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260823-1734-gen5-s5-intercepts-retry2",
|
|
"attempt": 2,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00017999999597668648,
|
|
"rollout/airborne_fraction": 0.3556901432573795,
|
|
"rollout/ep_len_mean": 113.32128012084961,
|
|
"rollout/ep_rew_mean": 26.062709903717042,
|
|
"rollout/forward_motion_fraction": 0.47930147713422777,
|
|
"rollout/goal_rate": 0.7368800011873246,
|
|
"rollout/grounded_upright_fraction": 0.17428000004589558,
|
|
"rollout/mean_altitude": 3.3864299325942993,
|
|
"rollout/productive_air_touch_fraction": 9.999999776482581e-05,
|
|
"rollout/upright_fraction": 0.7565201911926269,
|
|
"rollout/vertical_thrust_mean": 0.04238799838422798
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/goal_rate=0.7369 < 0.7500",
|
|
"rollout/productive_air_touch_fraction=0.0001 < 0.0050"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-24T07:07:11+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260823-1734-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 47,
|
|
"wins_b": 32,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 22,
|
|
"wins_b": 18,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 25,
|
|
"wins_b": 14,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 36,
|
|
"team_1": 43
|
|
},
|
|
"win_rate_a": 0.47
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-24T07:07:11+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260823-1734-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 47,
|
|
"wins_b": 32,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 22,
|
|
"wins_b": 18,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 25,
|
|
"wins_b": 14,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 36,
|
|
"team_1": 43
|
|
},
|
|
"win_rate_a": 0.47
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260824-1052-gen5-s5-intercepts",
|
|
"attempt": 0,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00025999999418854715,
|
|
"rollout/airborne_fraction": 0.3494572382569313,
|
|
"rollout/ball_above_air_touch_fraction": 0.44360085755586626,
|
|
"rollout/ball_mean_altitude": 4.1907234663963315,
|
|
"rollout/ball_peak_altitude": 5.405460600852966,
|
|
"rollout/ep_len_mean": 109.09664013671875,
|
|
"rollout/ep_rew_mean": 19.020949184417724,
|
|
"rollout/forward_motion_fraction": 0.50440152323246,
|
|
"rollout/goal_rate": 0.7694799978733062,
|
|
"rollout/grounded_upright_fraction": 0.1997999999076128,
|
|
"rollout/mean_altitude": 3.2880454597473143,
|
|
"rollout/productive_air_touch_episode_fraction": 3.999999910593033e-05,
|
|
"rollout/productive_air_touch_fraction": 3.999999910593033e-05,
|
|
"rollout/upright_fraction": 0.7768516182899475,
|
|
"rollout/vertical_thrust_mean": 0.09507499811029993
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0000 < 0.0200"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-25T07:35:28+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260824-1052-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 45,
|
|
"wins_b": 32,
|
|
"draws": 23,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 22,
|
|
"wins_b": 16,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 23,
|
|
"wins_b": 16,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.45
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-25T07:35:28+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260824-1052-gen5-s5-intercepts.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 45,
|
|
"wins_b": 32,
|
|
"draws": 23,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 22,
|
|
"wins_b": 16,
|
|
"draws": 12
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 23,
|
|
"wins_b": 16,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 38,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.45
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260825-0835-gen5-s5-intercepts-retry1",
|
|
"attempt": 1,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.0003199999928474426,
|
|
"rollout/airborne_fraction": 0.346053285330534,
|
|
"rollout/ball_above_air_touch_fraction": 0.4410076189041138,
|
|
"rollout/ball_mean_altitude": 4.184429080486297,
|
|
"rollout/ball_peak_altitude": 5.426401369094848,
|
|
"rollout/ep_len_mean": 102.62456001281738,
|
|
"rollout/ep_rew_mean": 17.775326847076418,
|
|
"rollout/forward_motion_fraction": 0.4838073335886002,
|
|
"rollout/goal_rate": 0.8083599947690964,
|
|
"rollout/grounded_upright_fraction": 0.18622000043094158,
|
|
"rollout/mean_altitude": 3.3077937359809875,
|
|
"rollout/productive_air_touch_episode_fraction": 5.9999998658895494e-05,
|
|
"rollout/productive_air_touch_fraction": 5.9999998658895494e-05,
|
|
"rollout/upright_fraction": 0.7801537146568298,
|
|
"rollout/vertical_thrust_mean": 0.1263369978432916
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0001 < 0.0200"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-26T05:31:14+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260825-0835-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 54,
|
|
"wins_b": 30,
|
|
"draws": 16,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 23,
|
|
"wins_b": 17,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 31,
|
|
"wins_b": 13,
|
|
"draws": 6
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 36,
|
|
"team_1": 48
|
|
},
|
|
"win_rate_a": 0.54
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-26T05:31:14+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260825-0835-gen5-s5-intercepts-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 54,
|
|
"wins_b": 30,
|
|
"draws": 16,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 23,
|
|
"wins_b": 17,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 31,
|
|
"wins_b": 13,
|
|
"draws": 6
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 36,
|
|
"team_1": 48
|
|
},
|
|
"win_rate_a": 0.54
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260826-0631-gen5-s5-intercepts-retry2",
|
|
"attempt": 2,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00025999999418854715,
|
|
"rollout/airborne_fraction": 0.3391489518582821,
|
|
"rollout/ball_above_air_touch_fraction": 0.4380011429786682,
|
|
"rollout/ball_mean_altitude": 4.176231199264526,
|
|
"rollout/ball_peak_altitude": 5.382643652915955,
|
|
"rollout/ep_len_mean": 106.93548004150391,
|
|
"rollout/ep_rew_mean": 18.05431349182129,
|
|
"rollout/forward_motion_fraction": 0.47924985593557357,
|
|
"rollout/goal_rate": 0.7813599967956543,
|
|
"rollout/grounded_upright_fraction": 0.1911600001603365,
|
|
"rollout/mean_altitude": 3.2340466198921205,
|
|
"rollout/productive_air_touch_episode_fraction": 1.9999999552965164e-05,
|
|
"rollout/productive_air_touch_fraction": 1.9999999552965164e-05,
|
|
"rollout/upright_fraction": 0.7784351890087128,
|
|
"rollout/vertical_thrust_mean": 0.11529199792654253
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0000 < 0.0200"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-27T03:26:36+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260826-0631-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 55,
|
|
"wins_b": 26,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 26,
|
|
"wins_b": 13,
|
|
"draws": 11
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 13,
|
|
"draws": 8
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.55
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-27T03:26:36+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260826-0631-gen5-s5-intercepts-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 55,
|
|
"wins_b": 26,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 26,
|
|
"wins_b": 13,
|
|
"draws": 11
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 29,
|
|
"wins_b": 13,
|
|
"draws": 8
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 39,
|
|
"team_1": 42
|
|
},
|
|
"win_rate_a": 0.55
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260827-0426-gen5-s5-intercepts-retry3",
|
|
"attempt": 3,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.0004399999901652336,
|
|
"rollout/airborne_fraction": 0.3489525710642338,
|
|
"rollout/ball_above_air_touch_fraction": 0.43863847601413725,
|
|
"rollout/ball_mean_altitude": 4.177910518169403,
|
|
"rollout/ball_peak_altitude": 5.388654420852661,
|
|
"rollout/ep_len_mean": 106.22960006713868,
|
|
"rollout/ep_rew_mean": 19.508184005737306,
|
|
"rollout/forward_motion_fraction": 0.4770670472383499,
|
|
"rollout/goal_rate": 0.7942799959182739,
|
|
"rollout/grounded_upright_fraction": 0.1820300002247095,
|
|
"rollout/mean_altitude": 3.3168045945167544,
|
|
"rollout/productive_air_touch_episode_fraction": 0.00017999999597668648,
|
|
"rollout/productive_air_touch_fraction": 0.00017999999597668648,
|
|
"rollout/upright_fraction": 0.7729688076972961,
|
|
"rollout/vertical_thrust_mean": 0.12024399826256559
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0002 < 0.0200"
|
|
],
|
|
"evaluation_goal_failures": [
|
|
"20260816-2126-gen5-s4-handling-retry2.json: goal_rate=0.710 < 0.750"
|
|
],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-28T01:14:11+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260827-0426-gen5-s5-intercepts-retry3.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 50,
|
|
"wins_b": 21,
|
|
"draws": 29,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 26,
|
|
"wins_b": 10,
|
|
"draws": 14
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 24,
|
|
"wins_b": 11,
|
|
"draws": 15
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 37,
|
|
"team_1": 34
|
|
},
|
|
"win_rate_a": 0.5
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-28T01:14:11+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260827-0426-gen5-s5-intercepts-retry3.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 50,
|
|
"wins_b": 21,
|
|
"draws": 29,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 26,
|
|
"wins_b": 10,
|
|
"draws": 14
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 24,
|
|
"wins_b": 11,
|
|
"draws": 15
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 37,
|
|
"team_1": 34
|
|
},
|
|
"win_rate_a": 0.5
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 1,
|
|
"stage_number": 5,
|
|
"stage_name": "intercepts",
|
|
"experiment": "20260828-0214-gen5-s5-intercepts-retry4",
|
|
"attempt": 4,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.0001599999964237213,
|
|
"rollout/airborne_fraction": 0.3465617146193981,
|
|
"rollout/ball_above_air_touch_fraction": 0.43904676276445387,
|
|
"rollout/ball_mean_altitude": 4.170995358467102,
|
|
"rollout/ball_peak_altitude": 5.4000493516922,
|
|
"rollout/ep_len_mean": 105.4797999420166,
|
|
"rollout/ep_rew_mean": 18.875109603881835,
|
|
"rollout/forward_motion_fraction": 0.49345138001441957,
|
|
"rollout/goal_rate": 0.7961599955558777,
|
|
"rollout/grounded_upright_fraction": 0.17021000032126904,
|
|
"rollout/mean_altitude": 3.3061050333976745,
|
|
"rollout/productive_air_touch_episode_fraction": 5.9999998658895494e-05,
|
|
"rollout/productive_air_touch_fraction": 5.9999998658895494e-05,
|
|
"rollout/upright_fraction": 0.7778172380924225,
|
|
"rollout/vertical_thrust_mean": 0.12272399805346504
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0001 < 0.0200"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-28T23:16:31+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 53,
|
|
"wins_b": 26,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 29,
|
|
"wins_b": 11,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 24,
|
|
"wins_b": 15,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 44,
|
|
"team_1": 35
|
|
},
|
|
"win_rate_a": 0.53
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-28T23:16:31+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 53,
|
|
"wins_b": 26,
|
|
"draws": 21,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 29,
|
|
"wins_b": 11,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 24,
|
|
"wins_b": 15,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 44,
|
|
"team_1": 35
|
|
},
|
|
"win_rate_a": 0.53
|
|
}
|
|
],
|
|
"decision": "pass",
|
|
"decision_override": {
|
|
"date": "2026-08-29",
|
|
"original_decision": "fail",
|
|
"original_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0001 < 0.0200"
|
|
],
|
|
"reason": "Human override. Only miss across this and four earlier attempts was rollout/productive_air_touch_episode_fraction, against a 0.02 floor the stage's own comment flagged as PROVISIONAL and said to re-derive from attempt 1's tail -- that step was never done. Attempt 1 (20260824) already measured 0.00004, ~500x under the floor, and the next three attempts (0.00006, 0.00002, 0.00018) plus this one (0.00006) show no trend toward 0.02, just noise at the same order of magnitude. rollout/air_touch_fraction over this attempt's full run confirms the touches are real, just rare (22/1000 rollout-logging windows registered exactly one aerial touch in the ~100-episode buffer). Every other gate passed comfortably: goal_rate 0.7962 vs 0.72, upright_fraction 0.7778 vs 0.40, forward_motion_fraction 0.4935 vs 0.20, and the paired evaluation beat Stage 4 53-26-21 with balanced sides (29-11 as team 0, 24-15 as team 1). Floor lowered 0.02 -> 0.00002 (the minimum of the five measured attempts) in generation5.py so it now tests real regression instead of an unvalidated guess. Stage 6 resumes from this checkpoint."
|
|
}
|
|
},
|
|
{
|
|
"stage_index": 2,
|
|
"stage_number": 6,
|
|
"stage_name": "league",
|
|
"experiment": "20260829-1649-gen5-s6-league",
|
|
"attempt": 0,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00017999999597668648,
|
|
"rollout/airborne_fraction": 0.3739089041352272,
|
|
"rollout/ball_above_air_touch_fraction": 0.3883678091168404,
|
|
"rollout/ball_mean_altitude": 3.96513764667511,
|
|
"rollout/ball_peak_altitude": 5.15273362159729,
|
|
"rollout/ep_len_mean": 85.36497992706299,
|
|
"rollout/ep_rew_mean": 32.01152058982849,
|
|
"rollout/forward_motion_fraction": 0.43747518974542615,
|
|
"rollout/goal_rate": 0.8620399980545044,
|
|
"rollout/grounded_upright_fraction": 0.135359999936074,
|
|
"rollout/mean_altitude": 3.712577560424805,
|
|
"rollout/productive_air_touch_episode_fraction": 0.00013999999687075616,
|
|
"rollout/productive_air_touch_fraction": 0.00013999999687075616,
|
|
"rollout/upright_fraction": 0.7597616654634476,
|
|
"rollout/vertical_thrust_mean": 0.15780499794334174
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0001 < 0.0150"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-08-31T06:21:58+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260829-1649-gen5-s6-league.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 32,
|
|
"wins_b": 51,
|
|
"draws": 17,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 17,
|
|
"wins_b": 24,
|
|
"draws": 9
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 15,
|
|
"wins_b": 27,
|
|
"draws": 8
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 44,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.32
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-08-31T06:21:58+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260829-1649-gen5-s6-league.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 32,
|
|
"wins_b": 51,
|
|
"draws": 17,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 17,
|
|
"wins_b": 24,
|
|
"draws": 9
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 15,
|
|
"wins_b": 27,
|
|
"draws": 8
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 44,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.32
|
|
},
|
|
{
|
|
"timestamp": "2026-08-31T06:23:16+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260829-1649-gen5-s6-league.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260806-1939-curric-s3-gauntlet.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 79,
|
|
"wins_b": 17,
|
|
"draws": 4,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 36,
|
|
"wins_b": 11,
|
|
"draws": 3
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 43,
|
|
"wins_b": 6,
|
|
"draws": 1
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 42,
|
|
"team_1": 54
|
|
},
|
|
"win_rate_a": 0.79
|
|
},
|
|
{
|
|
"timestamp": "2026-08-31T06:24:53+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260829-1649-gen5-s6-league.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 60,
|
|
"wins_b": 31,
|
|
"draws": 9,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 30,
|
|
"wins_b": 16,
|
|
"draws": 4
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 30,
|
|
"wins_b": 15,
|
|
"draws": 5
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 45,
|
|
"team_1": 46
|
|
},
|
|
"win_rate_a": 0.6
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 2,
|
|
"stage_number": 6,
|
|
"stage_name": "league",
|
|
"experiment": "20260831-0724-gen5-s6-league-retry1",
|
|
"attempt": 1,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00025999999418854715,
|
|
"rollout/airborne_fraction": 0.37644733387231827,
|
|
"rollout/ball_above_air_touch_fraction": 0.3837828570008278,
|
|
"rollout/ball_mean_altitude": 3.9463526849746704,
|
|
"rollout/ball_peak_altitude": 5.105142880439758,
|
|
"rollout/ep_len_mean": 84.73158009338378,
|
|
"rollout/ep_rew_mean": 29.349980991363527,
|
|
"rollout/forward_motion_fraction": 0.4234337618947029,
|
|
"rollout/goal_rate": 0.8689000006914139,
|
|
"rollout/grounded_upright_fraction": 0.1273200002387166,
|
|
"rollout/mean_altitude": 3.745820795059204,
|
|
"rollout/productive_air_touch_episode_fraction": 0.00011999999731779099,
|
|
"rollout/productive_air_touch_fraction": 0.00011999999731779099,
|
|
"rollout/upright_fraction": 0.7569749516248703,
|
|
"rollout/vertical_thrust_mean": 0.16791499748826028
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0001 < 0.0150"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-09-01T21:58:06+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260831-0724-gen5-s6-league-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 32,
|
|
"wins_b": 50,
|
|
"draws": 18,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 14,
|
|
"wins_b": 29,
|
|
"draws": 7
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 18,
|
|
"wins_b": 21,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.32
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-09-01T21:58:06+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260831-0724-gen5-s6-league-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 32,
|
|
"wins_b": 50,
|
|
"draws": 18,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 14,
|
|
"wins_b": 29,
|
|
"draws": 7
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 18,
|
|
"wins_b": 21,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 35,
|
|
"team_1": 47
|
|
},
|
|
"win_rate_a": 0.32
|
|
},
|
|
{
|
|
"timestamp": "2026-09-01T21:59:34+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260831-0724-gen5-s6-league-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260806-1939-curric-s3-gauntlet.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 79,
|
|
"wins_b": 15,
|
|
"draws": 6,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 40,
|
|
"wins_b": 9,
|
|
"draws": 1
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 39,
|
|
"wins_b": 6,
|
|
"draws": 5
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 46,
|
|
"team_1": 48
|
|
},
|
|
"win_rate_a": 0.79
|
|
},
|
|
{
|
|
"timestamp": "2026-09-01T22:01:35+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260831-0724-gen5-s6-league-retry1.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 54,
|
|
"wins_b": 29,
|
|
"draws": 17,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 26,
|
|
"wins_b": 18,
|
|
"draws": 6
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 28,
|
|
"wins_b": 11,
|
|
"draws": 11
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 37,
|
|
"team_1": 46
|
|
},
|
|
"win_rate_a": 0.54
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
},
|
|
{
|
|
"stage_index": 2,
|
|
"stage_number": 6,
|
|
"stage_name": "league",
|
|
"experiment": "20260901-2301-gen5-s6-league-retry2",
|
|
"attempt": 2,
|
|
"telemetry_tail": {
|
|
"rollout/air_touch_fraction": 0.00041999999061226843,
|
|
"rollout/airborne_fraction": 0.37447328644990924,
|
|
"rollout/ball_above_air_touch_fraction": 0.38510095232725144,
|
|
"rollout/ball_mean_altitude": 3.9452713265419006,
|
|
"rollout/ball_peak_altitude": 5.121470984458924,
|
|
"rollout/ep_len_mean": 88.07664016723633,
|
|
"rollout/ep_rew_mean": 29.80411368083954,
|
|
"rollout/forward_motion_fraction": 0.43738709545135496,
|
|
"rollout/goal_rate": 0.8521000001430511,
|
|
"rollout/grounded_upright_fraction": 0.15363000041246413,
|
|
"rollout/mean_altitude": 3.7138527517318725,
|
|
"rollout/productive_air_touch_episode_fraction": 0.0001599999964237213,
|
|
"rollout/productive_air_touch_fraction": 0.0001599999964237213,
|
|
"rollout/upright_fraction": 0.7552459052801133,
|
|
"rollout/vertical_thrust_mean": 0.15257299809571356
|
|
},
|
|
"telemetry_failures": [
|
|
"rollout/productive_air_touch_episode_fraction=0.0002 < 0.0150"
|
|
],
|
|
"evaluation_goal_failures": [],
|
|
"side_balance_failures": [],
|
|
"eval": {
|
|
"timestamp": "2026-09-03T10:42:38+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260901-2301-gen5-s6-league-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 31,
|
|
"wins_b": 50,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 16,
|
|
"wins_b": 24,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 15,
|
|
"wins_b": 26,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 42,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.31
|
|
},
|
|
"evals": [
|
|
{
|
|
"timestamp": "2026-09-03T10:42:38+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260901-2301-gen5-s6-league-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260828-0214-gen5-s5-intercepts-retry4.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 31,
|
|
"wins_b": 50,
|
|
"draws": 19,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 16,
|
|
"wins_b": 24,
|
|
"draws": 10
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 15,
|
|
"wins_b": 26,
|
|
"draws": 9
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 42,
|
|
"team_1": 39
|
|
},
|
|
"win_rate_a": 0.31
|
|
},
|
|
{
|
|
"timestamp": "2026-09-03T10:44:05+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260901-2301-gen5-s6-league-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260806-1939-curric-s3-gauntlet.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 80,
|
|
"wins_b": 14,
|
|
"draws": 6,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 38,
|
|
"wins_b": 9,
|
|
"draws": 3
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 42,
|
|
"wins_b": 5,
|
|
"draws": 3
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 43,
|
|
"team_1": 51
|
|
},
|
|
"win_rate_a": 0.8
|
|
},
|
|
{
|
|
"timestamp": "2026-09-03T10:46:05+00:00",
|
|
"model_a": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260901-2301-gen5-s6-league-retry2.json",
|
|
"model_b": "/home/jcreek/ai-training/CosmicClash/Game/bots/20260816-2126-gen5-s4-handling-retry2.json",
|
|
"seed": 1,
|
|
"episodes": 100,
|
|
"wins_a": 56,
|
|
"wins_b": 30,
|
|
"draws": 14,
|
|
"side_results": {
|
|
"a_team_0": {
|
|
"wins_a": 30,
|
|
"wins_b": 14,
|
|
"draws": 6
|
|
},
|
|
"a_team_1": {
|
|
"wins_a": 26,
|
|
"wins_b": 16,
|
|
"draws": 8
|
|
}
|
|
},
|
|
"physical_team_wins": {
|
|
"team_0": 46,
|
|
"team_1": 40
|
|
},
|
|
"win_rate_a": 0.56
|
|
}
|
|
],
|
|
"decision": "fail"
|
|
}
|
|
]
|
|
}
|