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
File diff suppressed because one or more lines are too long