Offline Reinforcement Learning on Atari Pong 1% DQN-replay v0
111.9Gamer-Normalized ScoreCQL
Evaluation Results
| Method | Links | |
|---|---|---|
| CQLdataset variant=1% DQN-replay2021.06 | 111.9 | |
| Decision Transformerdataset variant=1% DQN-replay2021.06 | 106.1 | |
| Behavior Cloningdataset variant=1% DQN-replay2021.06 | 85.2 | |
| QR-DQNdataset variant=1% DQN-replay2021.06 | 18 | |
| REMdataset variant=1% DQN-replay2021.06 | 0.5 |