Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

Benchmark Model Rank Results
openai-gym-on-ant-v4MEow#1Average Return: 6586.33
openai-gym-on-halfcheetah-v4MEow#4Average Return: 10981.47
openai-gym-on-hopper-v4MEow#1Average Return: 3332.99
openai-gym-on-humanoid-v4MEow#1Average Return: 6923.22
openai-gym-on-walker2d-v4MEow#2Average Return: 5526.66