Spaces:
Sleeping
Sleeping
Commit History
-
v0.6.0: make height_breach_penalty configurable per TetrisEnv instance
Allows Phase 1 (5 pieces) to disable height breach while Phase 2 enables it. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>86f507b -
v0.5.1: re-enable decaying height breach penalty from line 4
Height breach penalty back at -50/level, decaying by 5 per piece locked. Combined with 5-piece curriculum, teaches model not to stack high early. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>2038b66 -
v0.5.0: reduce game_over to -50, disable height breach penalty
Reward signal was dominated by constant penalties (-500 game over + ~-350 height breach), leaving only ~5% learnable signal. Now learnable components are ~80% of total reward. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>3a5b76e -
chore: add version string to game_engine.py (0.4.0)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>cd64402 -
feat: decaying height breach penalty based on pieces placed
Height breach penalty now decays by 5 per piece locked: piece 0 = -50/level, piece 9 = -5/level, piece 10+ = 0. Teaches model to keep board low early, relaxes later. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>9dd7378 -
feat: add one-time height breach penalty (-50 per level above 4)
First time the board height exceeds each level above 4, a -50 penalty is applied. This teaches the model to keep the board low. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>5a39470 -
fix: reduce step penalty from -1 to -0.1
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>2ced530 -
fix: remove height penalty, hole penalty only for new holes
Height penalty removed entirely. Hole penalty now only applies when a step creates new holes, not accumulated every step. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>49913c2 -
Rewrite play.html for per-piece training mode
- Per-piece tracking: shows current piece name, actions X/20 with progress bar that turns red near limit - Auto forced drop when 20 actions exceeded (with -10 penalty) - Game progress: total steps X/200, pieces placed, lines cleared - Training reward matches notebook: engine rewards + L/R penalty (-0.1) + piece placed bonus (+1) + no-place penalty (-10) + line clear bonus (+100/line) - Detects piece lock by comparing current_piece between responses - Removed old 100-action flat episode counter Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>cbba880 -
Fix play.html: 100 actions, fix horizontal expansion bug
- Change MAX_ACTIONS from 60 to 100 (match training notebook) - Update all UI text: "60 actions" → "100 actions" - Fix sidebar width to 260px (was min-width only, causing horizontal expansion as action log grew with each step) - Add overflow-x: hidden to action-log Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>b055f87
-
Training mode UI + single-char 60-action format
Web UI: - 60-action episode with progress bar (X/60) - Training reward displayed live (same formula as Cell 6) - Action log shows sequence as L R C W D S chars - Episode ends at 60 actions or game over - Keys: L/R/C/W/D/S match training encoding Notebook: - Cell 4: single-char format, 60 fixed actions - Cell 6: parse chars, pad/truncate to 60 - Cell 7: max_completion_length=128, RewardLogger callback Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>d69cfb4
-
Add playable Tetris web UI at /play
- Custom HTML page with rendered board grid, colors, stats - Keyboard controls: WASD/arrows, Space=drop, Q/E=rotate, R=reset - Click buttons for mobile - WebSocket connection to game engine - HF Spaces base_path changed to /play Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>1d19ab5 -
Upload src/tetris_env/server/game_engine.py with huggingface_hub
Verified signaturefe115bf -
Upload src/tetris_env/server/environment.py with huggingface_hub
Verified signatureba9aef4 -
Upload src/tetris_env/server/app.py with huggingface_hub
Verified signature21380cf -
Upload src/tetris_env/server/__init__.py with huggingface_hub
Verified signature20ac10c