Offline Reinforcement Learning on Atari 2600 Seaquest Minari (fixed offline dataset)
49Average Episodic ReturnERSAC-Ell-Epi*
Evaluation results
| Method | Links | |
|---|---|---|
| ERSAC-Ell-Epi*Offline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=3, Coverage parameter (υ)=0.92026.04 | 49 | |
| CQLOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=32026.04 | 47 | |
| ERSAC-Ell-NOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=3, Coverage parameter (υ)=0.92026.04 | 46 | |
| IQLOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=32026.04 | 45 | |
| ERSAC-CH-NOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=32026.04 | 42 | |
| SAC-NOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=32026.04 | 33 | |
| BRAC-BCQOffline training=true, Deterministic evaluation=true, Evaluation episodes=100, Random seeds=32026.04 | 18 |