Openai Gym On Walker2D V4

Average Return

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
SAC	5745.27	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
MEow	5526.66	Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
DDPG	2994.54	Continuous control with deep reinforcement learning
PPO	2739.81	Proximal Policy Optimization Algorithms
TD3	2612.74	Addressing Function Approximation Error in Actor-Critic Methods

0 of 5 row(s) selected.