5 Commits

Author	SHA1	Message	Date
Josh Creek	4e2d406aa2	chore(*): Remove run03 artifacts trained against the floor-taxed reward	2026-07-19 15:35:55 +01:00
CosmicClash Training Bot	5973d0893b	chore(training): Add run03 checkpoints, logs, and exported policy	2026-07-19 15:21:06 +01:00
Josh Creek	772f98b7fe	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	2026-07-19 13:21:14 +01:00
CosmicClash Training Bot	6f1a840249	chore(training): Add run02 checkpoints, logs, and exported policy	2026-07-19 12:41:44 +01:00
Josh Creek	85f96eb15e	feat(*): Add self-play RL training pipeline with PPO trainer, in-game GDScript policy inference, and bot opponent support in Match mode	2026-07-18 19:32:51 +01:00