Openai Gym On Humanoid V4

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

		Paper Title
MEow	6923.22	Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
SAC	6211.50	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
PPO	925.89	Proximal Policy Optimization Algorithms
TD3	198.44	Addressing Function Approximation Error in Actor-Critic Methods
DDPG	139.14	Continuous control with deep reinforcement learning

0 of 5 row(s) selected.