Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play

International Conference on Learning Representations (ICLR)


We describe a simple scheme that allows an agent to learn about its environment in an unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against one another. Alice proposes a task for Bob to complete; and then Bob attempts to complete the task. In this work we will focus on two kinds of environments: (nearly) reversible environments and environments that can be reset. Alice will “propose” the task by doing a sequence of actions and then Bob must undo or repeat them, respectively. Via an appropriate reward structure, Alice and Bob automatically generate a curriculum of exploration, enabling unsupervised training of the agent. When Bob is deployed on an RL task within the environment, this unsupervised training reduces the number of supervised episodes needed to learn, and in some cases converges to a higher reward.

Related Publications

All Publications

NeurIPS - December 5, 2021

Interpretable agent communication from scratch (with a generic visual processor emerging on the side)

Roberto Dessì, Eugene Kharitonov, Marco Baroni

Workshop on Online Abuse and Harms (WHOAH) at ACL - November 30, 2021

Findings of the WOAH 5 Shared Task on Fine Grained Hateful Memes Detection

Lambert Mathias, Shaoliang Nie, Bertie Vidgen, Aida Davani, Zeerak Waseem, Douwe Kiela, Vinodkumar Prabhakaran

Journal of Big Data - November 6, 2021

A graphical method of cumulative differences between two subpopulations

Mark Tygert

NeurIPS - December 6, 2021

Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement

Samuel Daulton, Maximilian Balandat, Eytan Bakshy

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookie Policy