HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Openai Gym On Hopper V4

Metrics

Average Return

Results

Performance results of various models on this benchmark

Paper TitleCode
MEow3332.99Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
TD33319.98Addressing Function Approximation Error in Actor-Critic Methods
SAC2882.56Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
DDPG1290.24Continuous control with deep reinforcement learning
PPO790.77Proximal Policy Optimization Algorithms
0 of 5 row(s) selected.