Partially observable navigation on Minigrid Maze2
97Solved RateACCEL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACCELBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 97 | |
| ADDBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=true2024.10 | 76 | |
| ADD w/o guidanceBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=false2024.10 | 62 | |
| PAIREDBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 60 | |
| DRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 46 | |
| PLRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 18 |