Spaces:
Sleeping
Sleeping
Commit History
-
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