Causal Reasoning from Meta-reinforcement Learning

Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-01
Main Authors: Dasgupta, Ishita, Wang, Jane, Chiappa, Silvia, Mitrovic, Jovana, Ortega, Pedro, Raposo, David, Hughes, Edward, Battaglia, Peter, Botvinick, Matthew, Kurth-Nelson, Zeb
Format: Article
Language:English
Subjects:
Intelligent agents
Machine learning
Markov analysis
Reasoning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal structure. We find that the trained agent can perform causal reasoning in novel situations in order to obtain rewards. The agent can select informative interventions, draw causal inferences from observational data, and make counterfactual predictions. Although established formal causal reasoning algorithms also exist, in this paper we show that such reasoning can arise from model-free reinforcement learning, and suggest that causal reasoning in complex settings may benefit from the more end-to-end learning-based approaches presented here. This work also offers new strategies for structured exploration in reinforcement learning, by providing agents with the ability to perform -- and interpret -- experiments.
ISSN:2331-8422