Goal Reaching on MiniGrid 8x8 Coordinates (test)
0.91Average RewardPPO (No defense)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PPO (No defense)Target Reward=0.96 ± 02024.06 | 0.91 | — | — | — | — | |
| TDRT-PPOTarget Reward=0.96 ± 02024.06 | 0.59 | — | — | — | — |
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PPO (No defense)Target Reward=0.96 ± 02024.06 | 0.91 | — | — | — | — | |
| TDRT-PPOTarget Reward=0.96 ± 02024.06 | 0.59 | — | — | — | — |