Reinforcement Learning on MiniGrid ObstructedMaze
7.4Success Rate (SR)LLM One-Shot
Evaluation results
| Method | Links | |
|---|---|---|
| LLM One-ShotTraining Episodes=3,0002026.05 | 7.4 | |
| LLM IterativeTraining Episodes=3,0002026.05 | 6.6 | |
| Hand-CraftedTraining Episodes=3,0002026.05 | 6.5 | |
| No ShapingTraining Episodes=3,0002026.05 | 0.5 | |
| RNDTraining Episodes=3,0002026.05 | 0 |