MuJoCo Reacher Environment

Overview

Make a 2D robot reach to a randomly located target.

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
-1.5 ACKTR Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
-1.7 A2C Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
-2.0 TRPO Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
-3.6 TD3 Addressing Function Approximation Error in Actor-Critic Methods
-4.01 Our DDPG Addressing Function Approximation Error in Actor-Critic Methods
-4.26 ACKTR Addressing Function Approximation Error in Actor-Critic Methods
-4.44 SAC Addressing Function Approximation Error in Actor-Critic Methods
-4.82 TRPO (MPI) OpenAI Baselines ea68f3b
-6.18 PPO Addressing Function Approximation Error in Actor-Critic Methods
-6.51 DDPG Addressing Function Approximation Error in Actor-Critic Methods
-6.71 PPO OpenAI Baselines ea68f3b
-111.43 TRPO Addressing Function Approximation Error in Actor-Critic Methods