Openai Gym On Ant V4

Average Return

Results

Performance results of various models on this benchmark

		Paper Title
MEow	6586.33	Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
TD3	5942.55	Addressing Function Approximation Error in Actor-Critic Methods
SAC	5208.09	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
DDPG	1712.12	Continuous control with deep reinforcement learning
PPO	608.97	Proximal Policy Optimization Algorithms

0 of 5 row(s) selected.