Learning policy representations in multiagent systems
Captured source
source ↗Learning policy representations in multiagent systems | OpenAI
June 17, 2018
Learning policy representations in multiagent systems
Loading…
Share
Abstract
Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general learning framework for modeling agent behavior in any multiagent system using only a handful of interaction data. Our framework casts agent modeling as a representation learning problem. Consequently, we construct a novel objective inspired by imitation learning and agent identification and design an algorithm for unsupervised learning of representations of agent policies. We demonstrate empirically the utility of the proposed framework in (i) a challenging high-dimensional competitive environment for continuous control and (ii) a cooperative environment for communication, on supervised predictive tasks, unsupervised clustering, and policy optimization using deep reinforcement learning.
Authors
Aditya Grover, Maruan Al-Shedivat, Jayesh K. Gupta, Yura Burda, Harri Edwards
Related articles
Scaling laws for reward model overoptimizationPublicationOct 19, 2022
Learning to play Minecraft with Video PreTrainingConclusionJun 23, 2022
Dota 2 with large scale deep reinforcement learningPublicationDec 13, 2019
Notability
Scored, but no written rationale attached yet.
OpenAI has a writing signal matching infrastructure, safety and policy.