Action control, forward models and expected rewards: representations in reinforcement learning

Synthese 199 (5-6):14017-14033 (2021)
  Copy   BIBTEX

Abstract

The fundamental cognitive problem for active organisms is to decide what to do next in a changing environment. In this article, we analyze motor and action control in computational models that utilize reinforcement learning (RL) algorithms. In reinforcement learning, action control is governed by an action selection policy that maximizes the expected future reward in light of a predictive world model. In this paper we argue that RL provides a way to explicate the so-called action-oriented views of cognitive systems in representational terms.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 90,593

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Learning to Signal in a Dynamic World.J. McKenzie Alexander - 2014 - British Journal for the Philosophy of Science 65 (4):797-820.
Models as Relational Categories.Tommi Kokkonen - 2017 - Science & Education 26 (7-9):777-798.

Analytics

Added to PP
2022-01-05

Downloads
12 (#929,405)

6 months
3 (#445,838)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

Jesse Kuokkanen
University of Helsinki
Anna-Mari Rusanen
University of Helsinki

Citations of this work

No citations found.

Add more citations