Openai Gym On Hopper V4

Average Return

Résultats

Résultats de performance de divers modèles sur ce benchmark

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

0 of 5 row(s) selected.