Offline Reinforcement Learning on Atari Seaquest 1% DQN-replay v0
2.5Gamer-Normalized ScoreDecision Transformer
Evaluation Results
| Method | Links | |
|---|---|---|
| Decision Transformerdataset variant=1% DQN-replay2021.06 | 2.5 | |
| Behavior Cloningdataset variant=1% DQN-replay2021.06 | 2.1 | |
| CQLdataset variant=1% DQN-replay2021.06 | 1.7 | |
| REMdataset variant=1% DQN-replay2021.06 | 0.7 | |
| QR-DQNdataset variant=1% DQN-replay2021.06 | 0.4 |