Partially observable navigation on Minigrid Labyrinth
100Solved RateADD
Evaluation Results
| Method | Links | |
|---|---|---|
| ADDBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=true2024.10 | 100 | |
| ACCELBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 96 | |
| DRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 74 | |
| PAIREDBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 74 | |
| PLRBase algorithm=LSTM-based PPO, Environmental steps=250M2024.10 | 63 | |
| ADD w/o guidanceBase algorithm=LSTM-based PPO, Environmental steps=250M, Guidance=false2024.10 | 56 |