Awesome Open Source
Awesome Open Source

Self-Supervised Exploration via Disagreement

[Project Website] [Demo Video]

Deepak Pathak*, Dhiraj Gandhi*, Abhinav Gupta
(* equal contribution)

UC Berkeley
Facebook AI Research

This is a TensorFlow based implementation for our paper on self-supervised exploration via disagreement. In this paper, we propose a formulation for exploration inspired by the work in active learning literature. Specifically, we train an ensemble of dynamics models and incentivize the agent to explore such that the disagreement of those ensembles is maximized. This allows the agent to learn skills by exploring in a self-supervised manner without any external reward. Notably, we further leverage the disagreement objective to optimize the agent's policy in a differentiable manner, without using reinforcement learning, which results in a sample-efficient exploration. We demonstrate the efficacy of this formulation across a variety of benchmark environments including stochastic-Atari, Mujoco, Unity and a real robotic arm. If you find this work useful in your research, please cite:

    Author = {Pathak, Deepak and
              Gandhi, Dhiraj and Gupta, Abhinav},
    Title = {Self-Supervised Exploration via Disagreement},
    Booktitle = {ICML},
    Year = {2019}

Installation and Usage

The following command should train a pure exploration agent on Breakout with default experiment parameters.


To use more than one gpu/machine, use MPI (e.g. mpiexec -n 8 python should use 1024 parallel environments to collect experience instead of the default 128 on an 8 gpu machine).

Other helpful pointers


This repository is built off the publicly released code of Large-Scale Study of Curiosity-driven Learning, ICLR 2019.

Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (795,861
Deep Learning (35,987
Tensorflow (22,282
Paper (18,795
Artificial Intelligence (18,753
Rl (2,338
Deep Reinforcement Learning (1,007
Exploration (99
Self Supervised (40
Curiosity (29