Continuous Control on Ant v4 (Interaction Count)
98Interaction Count ($10^4$ steps)PPO
Evaluation results
| Method | Links | |
|---|---|---|
| PPOCritic Learning Rate=3e-4, Actor Learning Rate=3e-4, Actor and Critic Structure=(64, 64), Batch Size=322025.05 | 98 | |
| TD3Critic Learning Rate=3e-4, Actor Learning Rate=3e-4, Actor and Critic Structure=(256, 256), Batch Size=2562025.05 | 77 | |
| SACCritic Learning Rate=3e-4, Actor Learning Rate=3e-4, Actor and Critic Structure=(256, 256), Batch Size=2562025.05 | 30 | |
| SD3Critic Learning Rate=1e-3, Actor Learning Rate=1e-3, Actor and Critic Structure=(256, 256), Batch Size=2562025.05 | 28 | |
| CSACCritic Learning Rate=3e-4, Actor Learning Rate=3e-4, Actor and Critic Structure=(256, 256), Batch Size=2562025.05 | 22.5 |