|
.gitignore
|
tetris
|
2026-10-01 08:27:39 -04:00 |
|
human_tetris_1.jsonl
|
rework sft
|
2026-10-01 08:52:36 -04:00 |
|
play_tetris_oracle.py
|
tetris
|
2026-10-01 08:27:39 -04:00 |
|
RL_TRAINING.md
|
guh
|
2026-10-01 13:12:00 -04:00 |
|
sft_tetris.py
|
WSD for sft
|
2026-10-01 09:03:19 -04:00 |
|
test_tetris_rewards.py
|
guh
|
2026-10-01 13:12:00 -04:00 |
|
test_tetris_rl.py
|
guh
|
2026-10-01 13:12:00 -04:00 |
|
tetris.py
|
rework RL pipeline
|
2026-10-01 10:01:25 -04:00 |
|
tetris_datagen.py
|
rework sft
|
2026-10-01 08:52:36 -04:00 |
|
tetris_oracle.py
|
rework RL pipeline
|
2026-10-01 10:01:25 -04:00 |
|
tetris_policy.py
|
tetris
|
2026-10-01 08:27:39 -04:00 |
|
tetris_rewards.py
|
guh
|
2026-10-01 13:12:00 -04:00 |
|
train_tetris_oracle.py
|
rework RL pipeline
|
2026-10-01 10:01:25 -04:00 |
|
train_tetris_rl.py
|
guh
|
2026-10-01 13:12:00 -04:00 |