/ERL

Code accompanying the paper "Evolution-Guided Policy Gradients in Reinforcement Learning" accepted at NIPS 2018

Primary LanguagePython

AADI ERL Implementation

Code adapted from the paper "Evolution-Guided Policy Gradients in Reinforcement Learning" accepted at NIPS 2018

External Dependencies
  • Python 3.5.6
  • Mujoco-py v1.50.1.59

All other dependencies are listed in the requirements.txt file

To Run

python run_erl.py -env $ENV_NAME$

ENVS TESTED

'Hopper-v2'
'HalfCheetah-v2'
'Swimmer-v2'
'Ant-v2'
'Walker2d-v2'
'Reacher-v2'