Reinforcement Learning on Pendulum v1 (test)
-164.82Average ReturnRSA2C-KME
Evaluation results
| Method | Links | |
|---|---|---|
| RSA2C-KMENoise variance=02025.12 | -164.82 | |
| SACNoise variance=02025.12 | -169.07 | |
| SACNoise variance=0.0012025.12 | -170.05 | |
| RSA2C-CMENoise variance=02025.12 | -170.24 | |
| SACNoise variance=0.0052025.12 | -171.58 | |
| RSA2C-CMENoise variance=0.0052025.12 | -172.19 | |
| SACNoise variance=0.012025.12 | -172.79 | |
| RSA2C-CMENoise variance=0.012025.12 | -176.1 | |
| RSA2C-CMENoise variance=0.0012025.12 | -180.96 | |
| PPONoise variance=0.0052025.12 | -201.6 | |
| PPONoise variance=02025.12 | -217.68 | |
| PPONoise variance=0.012025.12 | -219.09 | |
| PPONoise variance=0.0012025.12 | -219.36 | |
| RSA2C-KMENoise variance=0.012025.12 | -268.61 | |
| RSA2C-KMENoise variance=0.0052025.12 | -296.74 | |
| RSA2C-KMENoise variance=0.0012025.12 | -316.48 |