OutOfMystic Claude Opus 4.6 commited on
Commit
2ced530
·
1 Parent(s): 49913c2

fix: reduce step penalty from -1 to -0.1

Browse files

Step penalty of -1 was punishing the model for surviving longer,
making death the optimal strategy. Reduced to -0.1.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/tetris_env/server/game_engine.py CHANGED
@@ -37,7 +37,7 @@ LINE_REWARDS = {
37
  4: 1500, # "Tetris!" — the dream
38
  }
39
 
40
- STEP_PENALTY = -1
41
  HOLE_PENALTY_MULT = -5
42
  GAME_OVER_PENALTY = -500
43
 
 
37
  4: 1500, # "Tetris!" — the dream
38
  }
39
 
40
+ STEP_PENALTY = -0.1
41
  HOLE_PENALTY_MULT = -5
42
  GAME_OVER_PENALTY = -500
43