Igor Mordatch
10 posts
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.