MuJoCo Swimmer Environment

Overview

Make a 2D robot swim.

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
297.0 Trust-PCL Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
288.1 TRPO Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
140.7 A2C Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
138.0 ACKTR Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
137.25 TRPO+GAE Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
136.4 TRPO Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
111.19 PPO OpenAI Baselines ea68f3b
94.96 TRPO (MPI) OpenAI Baselines ea68f3b