Value Of Information And Reward Specification In Active Inference And Pomdps

Abstract

Expected free energy (EFE) is a central quantity in active inference which has recently gained popularity due to its intuitive decomposition of the expected value of control into a pragmatic and an epistemic component. While numerous conjectures have been made to justify EFE as a decision making objective function, the most widely accepted is still its intuitiveness and resemblance to variational free energy in approximate Bayesian inference. In this work, we take a bottom up approach and ask: taking EFE as given, what's the resulting agent's optimality gap compared with a reward-driven reinforcement learning (RL) agent, which is well understood? By casting EFE under a particular class of belief MDP and using analysis tools from RL theory, we show that EFE approximates the Bayes optimal RL policy via information value. We discuss the implications for objective specification of active inference agents.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywei2024value

Related papers

• Prior Preference Learning From Experts:designing A Reward With Active Inference (2021)0.00
• Reward Maximisation Through Discrete Active Inference (2020)10.74
• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• Active Inference As A Model Of Agency (2024)0.00
• Sophisticated Inference (2020)14.83
• Information Directed Reward Learning For Reinforcement Learning (2021)0.00
• Modulation Of Viability Signals For Self-regulatory Control (2020)0.00
• Understanding The Origin Of Information-seeking Exploration In Probabilistic Objectives For Control (2021)0.00