Robot Control on PandaReach v2
-2.04Max Average ReturnConservative Soft Actor-Critic
Evaluation results
| Method | Links | |
|---|---|---|
| Conservative Soft Actor-Critic2025.05 | -2.04 | |
| SAC2025.05 | -2.12 | |
| SD32025.05 | -48.36 | |
| TD32025.05 | -48.57 | |
| PPO2025.05 | -49.8 |
| Method | Links | |
|---|---|---|
| Conservative Soft Actor-Critic2025.05 | -2.04 | |
| SAC2025.05 | -2.12 | |
| SD32025.05 | -48.36 | |
| TD32025.05 | -48.57 | |
| PPO2025.05 | -49.8 |