Openai Gym On Ant 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
模型名称 | Average Return | Paper Title | Repository |
|---|---|---|---|
| PPO | 608.97 | Proximal Policy Optimization Algorithms | |
| DDPG | 1712.12 | Continuous control with deep reinforcement learning | |
| TD3 | 5942.55 | Addressing Function Approximation Error in Actor-Critic Methods | |
| MEow | 6586.33 | Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow | |
| SAC | 5208.09 | Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor |
0 of 5 row(s) selected.