Partially observable navigation on Minigrid Maze
82Solved RateACCEL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACCELBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 82 | |
| ADDBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=true2024.10 | 79 | |
| DRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 36 | |
| PLRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 21 | |
| ADD w/o guidanceBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=false2024.10 | 18 | |
| PAIREDBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 6 |