English | 简体中文

ESBox is an efficient tool for black-box optimization with multiple evolutionary strategy algorithms.

git clone https://github.com/ShuaibinLi/ESBox.git
cd ESBox
pip install . 

• parl
• pytorch or paddlepaddle
• gym==0.18.0
• mujoco-py==2.1.2.14
  Note: To use mujoco-v2 env in gym0.18.0, please download the mujoco210 binaries for Linux and extract the downloaded mujoco210 directory into ~/.mujoco/mujoco210.

• Two training methods: local training and distributed training
• Two forms of optimization: Model optimization (CartPole-v1 as an example) and float List optimization (2-dimensional 2nd degree function as an example)

• Examples of five algorithms that solve two categories of problems
• The results of the benchmark reproduction