FEPS agents combine projective simulation with active inference to learn world models and goal-directed policies from prediction accuracy alone, resolving ambiguous observations without external rewards.
Value of Information and Reward Specification in Active Inference and POMDPs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Free Energy Projective Simulation (FEPS): Active inference with interpretability
FEPS agents combine projective simulation with active inference to learn world models and goal-directed policies from prediction accuracy alone, resolving ambiguous observations without external rewards.