feat(*): Fix exported-policy action order to gymnasium's sorted-key layout, add wall-contact penalty and stronger ball-touch reward, and wire Spectate to run01 vs run02

This commit is contained in:
Josh Creek
2026-07-19 13:21:14 +01:00
parent 6f1a840249
commit 772f98b7fe
6 changed files with 34 additions and 8 deletions
+10
View File
@@ -8,5 +8,15 @@
"wins_b": 0,
"draws": 5,
"win_rate_a": 0.167
},
{
"timestamp": "2026-07-19T12:11:30+00:00",
"model_a": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run01.json",
"model_b": "/Users/jcreek/Documents/repos/GitHub/CosmicClash/Game/bots/run02.json",
"episodes": 40,
"wins_a": 4,
"wins_b": 1,
"draws": 35,
"win_rate_a": 0.1
}
]