/Empowerment-driven-Exploration

Tensorflow implementation for Empowerment driven Exploration using Mutual Information Estimation

Primary LanguagePython

Empowerment driven Exploration using Mutual Information Estimation

Code inspired by Exploration using Random Distillation

Installation and Usage

The following command should train an Empowerment agent on Montezuma's Revenge

python run_atari.py --gamma_ext 0.999

To use more than one gpu/machine, use MPI (e.g. mpiexec -n 8 python run_atari.py --num_env 128 --gamma_ext 0.999 should use 1024 parallel environments to collect experience on an 8 gpu machine).

Blog post