Deep Active Inference For Partially Observable Mdps

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.

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyvanderhimst2020deep

Related papers

• Deep Active Inference Agents Using Monte-carlo Methods (2020)0.00
• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• Deconstructing Deep Active Inference (2023)2.26
• Deepmdp: Learning Continuous Latent Space Models For Representation Learning (2019)0.00
• Learning Interpretable Policies In Hindsight-observable Pomdps Through Partially Supervised Reinforcement Learning (2024)2.26
• A Deep Policy Inference Q-network For Multi-agent Systems (2017)0.00
• Active Inference: Demystified And Compared (2019)15.98
• Low-dimensional State And Action Representation Learning With MDP Homomorphism Metrics (2021)0.00