Openai Gym On Halfcheetah V4

Average Return

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average Return	Paper Title
DDPG	14934.86	Continuous control with deep reinforcement learning
SAC	15836.04	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
TD3	12026.73	Addressing Function Approximation Error in Actor-Critic Methods
MEow	10981.47	Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
PPO	6006.11	Proximal Policy Optimization Algorithms

0 of 5 row(s) selected.