Emergent Tool Use from Multi-Agent Interaction

We've observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek.

Implicit Generation and Generalization Methods for Energy-Based Models

Neural MMO: A Massively Multiagent Game Environment

Learning Concepts with Energy Functions

OpenAI Fellows Fall 2018

Interpretable Machine Learning through Teaching

Meta-Learning for Wrestling

Competitive Self-Play

We've found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind.

Learning to Model Other Minds

Learning to Cooperate, Compete, and Communicate

Learning to Communicate