Overview

Make a 2D cheetah robot run.

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
9636.95 TD3 Addressing Function Approximation Error in Actor-Critic Methods
8577.29 Our DDPG Addressing Function Approximation Error in Actor-Critic Methods
7057.1 Trust-PCL Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
5704.7 TRPO Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
5586.3 ACKTR Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
5343.7 A2C Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
4871.36 TRPO+GAE Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
4343.6 TRPO Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
3305.6 DDPG Addressing Function Approximation Error in Actor-Critic Methods
2347.19 SAC Addressing Function Approximation Error in Actor-Critic Methods
1795.43 PPO Addressing Function Approximation Error in Actor-Critic Methods
1668.58 PPO OpenAI Baselines ea68f3b
1450.46 ACKTR Addressing Function Approximation Error in Actor-Critic Methods
1289.7 TRPO (MPI) OpenAI Baselines ea68f3b
-15.57 TRPO Addressing Function Approximation Error in Actor-Critic Methods