mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-10 16:04:04 +00:00
511 lines
16 KiB
JSON
511 lines
16 KiB
JSON
{
|
|
"stage_index": 1,
|
|
"attempt": 2,
|
|
"status": "blocked",
|
|
"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"
|
|
}
|
|
]
|
|
}
|