Behavior Cloning on Maze2D (test)
2.74RewardDecision-GPT
Evaluation Results
| Method | Links | |
|---|---|---|
| Decision-GPTContext Length=102022.11 | 2.74 | |
| Uni[MASK] - multi-task + finetuneContext Length=52022.11 | 2.73 | |
| Uni[MASK] - finetuneContext Length=52022.11 | 2.67 | |
| Uni[MASK] - single-taskContext Length=52022.11 | 2.66 | |
| Decision-GPTContext Length=52022.11 | 2.66 | |
| Uni[MASK] - multi-task (BC & RC)Context Length=52022.11 | 2.65 | |
| Uni[MASK] - finetuneContext Length=102022.11 | 2.55 | |
| Uni[MASK] - single-taskContext Length=102022.11 | 2.47 | |
| Uni[MASK] - multi-task + finetuneContext Length=102022.11 | 2.42 | |
| Uni[MASK] - multi-task (BC & RC)Context Length=102022.11 | 2.39 | |
| Uni[MASK] - random-maskContext Length=102022.11 | 2.29 | |
| Uni[MASK] - random-maskContext Length=52022.11 | 2.19 | |
| Feedforward Neural NetworkContext Length=102022.11 | 1.83 | |
| Feedforward Neural NetworkContext Length=52022.11 | 1.68 | |
| Decision TransformerContext Length=102022.11 | 1.58 | |
| Decision TransformerContext Length=52022.11 | 1.13 |