MuJoCo Ant Environment

Overview

Make a four-legged creature 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
6104.2 Trust-PCL Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
5095.0 TRPO Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
4870.5 A2C Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
4621.6 ACKTR Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
4372.44 TD3 Addressing Function Approximation Error in Actor-Critic Methods
4347.5 TRPO Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
2918.25 TRPO+GAE Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
1821.94 ACKTR Addressing Function Approximation Error in Actor-Critic Methods
1083.2 PPO Addressing Function Approximation Error in Actor-Critic Methods
1005.3 DDPG Addressing Function Approximation Error in Actor-Critic Methods
888.77 Our DDPG Addressing Function Approximation Error in Actor-Critic Methods
655.35 SAC Addressing Function Approximation Error in Actor-Critic Methods
-75.85 TRPO Addressing Function Approximation Error in Actor-Critic Methods