Deep Active Inference for Partially Observable MDPs

Code

• github.com/Grottoh/Deep-Active-Inference-for-Partially-Observable-MDPs
  OfficialIn paperpytorch★ 26

Abstract

Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces. However, current models are limited to fully observable domains. In this paper, we describe a deep active inference model that can learn successful policies directly from high-dimensional sensory inputs. The deep learning architecture optimizes a variant of the expected free energy and encodes the continuous state representation by means of a variational autoencoder. We show, in the OpenAI benchmark, that our approach has comparable or better performance than deep Q-learning, a state-of-the-art deep reinforcement learning algorithm.

Tasks

Reproductions