Partially observable navigation on Minigrid PerfectMaze (M)
82Solved RateADD
Evaluation Results
| Method | Links | |
|---|---|---|
| ADDBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=true2024.10 | 82 | |
| ACCELBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 64 | |
| DRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 45 | |
| ADD w/o guidanceBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=false2024.10 | 45 | |
| PAIREDBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 43 | |
| PLRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 37 |