Reinforcement Learning on MiniGrid MultiRoom-N6
50Success RateLLM One-Shot
Evaluation results
| Method | Links | |
|---|---|---|
| LLM One-ShotTraining Episodes=3,0002026.05 | 50 | |
| LLM IterativeTraining Episodes=3,0002026.05 | 30 | |
| No ShapingTraining Episodes=3,0002026.05 | 0 | |
| Hand-CraftedTraining Episodes=3,0002026.05 | 0 | |
| RNDTraining Episodes=3,0002026.05 | 0 |