Safe Reinforcement Learning on Paddle-Juggler 100 rollouts
100ACSOurs
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Oursrollouts=1002026.04 | 100 | 100 | |
| TD3rollouts=1002026.04 | 99 | 50 | |
| PPO Barrierrollouts=1002026.04 | 99 | 49 | |
| CPOrollouts=1002026.04 | 90 | 45 |
| Method | Links | ||
|---|---|---|---|
| Oursrollouts=1002026.04 | 100 | 100 | |
| TD3rollouts=1002026.04 | 99 | 50 | |
| PPO Barrierrollouts=1002026.04 | 99 | 49 | |
| CPOrollouts=1002026.04 | 90 | 45 |