Temporal-difference reinforcement learning with distributed representations.

• Main Authors: Zeb Kurth-Nelson, A David Redish
• Format: Article
• Language: English
• Published: Public Library of Science (PLoS) 2009-10-01
• Series: PLoS ONE
• Online Access: https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/19841749/pdf/?tool=EBI

Temporal-difference (TD) algorithms have been proposed as models of reinforcement learning (RL). We examine two issues of distributed representation in these TD algorithms: distributed representations of belief and distributed discounting factors. Distributed representation of belief allows the believed state of the world to distribute across sets of equivalent states. Distributed exponential discounting factors produce hyperbolic discounting in the behavior of the agent itself. We examine these issues in the context of a TD RL model in which state-belief is distributed over a set of exponentially-discounting "micro-Agents", each of which has a separate discounting factor (gamma). Each microAgent maintains an independent hypothesis about the state of the world, and a separate value-estimate of taking actions within that hypothesized state. The overall agent thus instantiates a flexible representation of an evolving world-state. As with other TD models, the value-error (delta) signal within the model matches dopamine signals recorded from animals in standard conditioning reward-paradigms. The distributed representation of belief provides an explanation for the decrease in dopamine at the conditioned stimulus seen in overtrained animals, for the differences between trace and delay conditioning, and for transient bursts of dopamine seen at movement initiation. Because each microAgent also includes its own exponential discounting factor, the overall agent shows hyperbolic discounting, consistent with behavioral experiments.