MuJoCo Walker2D Environment

Overview

Make a two-dimensional bipedal robot walk forward as fast as possible.

Performances of RL Agents

We list various reinforcement learning algorithms that were tested in this environment. These results are from RL Database. If this page was helpful, please consider giving a star!

Star

Result Algorithm Source
6874.1 TRPO Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
6198.8 ACKTR Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
6028.73 TRPO+GAE Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
5874.9 A2C Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
5027.2 Trust-PCL Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
4682.82 TD3 Addressing Function Approximation Error in Actor-Critic Methods
3424.95 PPO OpenAI Baselines ea68f3b
3317.69 PPO Addressing Function Approximation Error in Actor-Critic Methods
3098.11 Our DDPG Addressing Function Approximation Error in Actor-Critic Methods
2838.4 TRPO Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
2342.63 TRPO (MPI) OpenAI Baselines ea68f3b
2321.47 TRPO Addressing Function Approximation Error in Actor-Critic Methods
1843.85 DDPG Addressing Function Approximation Error in Actor-Critic Methods
1283.67 SAC Addressing Function Approximation Error in Actor-Critic Methods
1216.7 ACKTR Addressing Function Approximation Error in Actor-Critic Methods