Active Inference: Demystified And Compared

Abstract

Active inference is a first principle account of how autonomous agents operate in dynamic, non-stationary environments. This problem is also considered in reinforcement learning (RL), but limited work exists on comparing the two approaches on the same discrete-state environments. In this paper, we provide: 1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in RL; 2) an explicit discrete-state comparison between active inference and RL on an OpenAI gym baseline. We begin by providing a condensed overview of the active inference literature, in particular viewing the various natural behaviors of active inference agents through the lens of RL. We show that by operating in a pure belief-based setting, active inference agents can carry out epistemic exploration, and account for uncertainty about their environment in a Bayes-optimal fashion. Furthermore, we show that the reliance on

Stats

• citations134
• S2 citations—
• github stars0
• HF likes0
• heat score15.98
• arxiv keysajid2019active

Related papers

• Deconstructing Deep Active Inference (2023)2.26
• Active Inference As A Model Of Agency (2024)0.00
• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• Sophisticated Inference (2020)14.83
• Contrastive Active Inference (2021)0.00
• Deep Active Inference Agents Using Monte-carlo Methods (2020)0.00
• Reward Maximisation Through Discrete Active Inference (2020)10.74
• Expanding The Active Inference Landscape: More Intrinsic Motivations In The Perception-action Loop (2018)9.92