Robot Navigation on DoggoGoal
21.3Episodic RewardPPO
Evaluation results
| Method | Links | |
|---|---|---|
| PPOLearning Category=Model-free2022.10 | 21.3 | |
| PPO-LagrangianLearning Category=Model-free2022.10 | 1.6275 | |
| safe-LOOPLearning Category=Model-based2022.10 | -0.14 | |
| MBPPO-LagrangianLearning Category=Model-based2022.10 | -0.69 |