Openai Gym On Humanoid V4
评估指标
Average Return
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Average Return |
|---|---|
| soft-actor-critic-off-policy-maximum-entropy | 6211.50 |
| maximum-entropy-reinforcement-learning-via | 6923.22 |
| continuous-control-with-deep-reinforcement | 139.14 |
| addressing-function-approximation-error-in | 198.44 |
| proximal-policy-optimization-algorithms | 925.89 |