Bayesian policy selection using active inference

Abstract

Learning to take actions based on observations is a core requirement for artificial agents to be able to be successful and robust at their task. Reinforcement Learning (RL) is a well-known technique for learning such policies. However, current RL algorithms often have to deal with reward shaping, have difficulties generalizing to other environments and are most often sample inefficient. In this paper, we explore active inference and the free energy principle, a normative theory from neuroscience that explains how self-organizing biological systems operate by maintaining a model of the world and casting action selection as an inference problem. We apply this concept to a typical problem known to the RL community, the mountain car problem, and show how active inference encompasses both RL and learning from demonstrations.

ICLR 2019 Workshop on Structure & priors in reinforcement learning

References in corpus (5)

• Auto-Encoding Variational Bayes
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
• Universal Planning Networks

Cited by in corpus (6)

• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Deep active inference agents using Monte-Carlo methods
• Deep Active Inference for Autonomous Robot Navigation
• Application of the Free Energy Principle to Estimation and Control
• Active Inference for Stochastic Control
• Episodic Memory for Learning Subjective-Timescale Models