Openai Gym On Hopper V4

Average Return

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average Return	Paper Title
DDPG	1290.24	Continuous control with deep reinforcement learning
MEow	3332.99	Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
TD3	3319.98	Addressing Function Approximation Error in Actor-Critic Methods
PPO	790.77	Proximal Policy Optimization Algorithms
SAC	2882.56	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

0 of 5 row(s) selected.