Openai Gym On Hopper V4
評価指標
Average Return
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Average Return |
|---|---|
| continuous-control-with-deep-reinforcement | 1290.24 |
| maximum-entropy-reinforcement-learning-via | 3332.99 |
| addressing-function-approximation-error-in | 3319.98 |
| proximal-policy-optimization-algorithms | 790.77 |
| soft-actor-critic-off-policy-maximum-entropy | 2882.56 |