Heist on Procgen easy
1.87Mean Episode ReturnPPO
Evaluation Results
| Method | Links | |
|---|---|---|
| PPOTraining steps=25M, Difficulty mode=easy, Seeds=3, Eval episodes per seed=252026.02 | 1.87 | |
| BPPOTraining steps=25M, Difficulty mode=easy, Seeds=3, Eval episodes per seed=252026.02 | 1.87 | |
| TRPO-KLTraining steps=25M, Difficulty mode=easy, Seeds=3, Eval episodes per seed=252026.02 | 0.67 | |
| BTRPO-BCTraining steps=25M, Difficulty mode=easy, Seeds=3, Eval episodes per seed=252026.02 | 0.67 |