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.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 99,484

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

Reinforcement learning and artificial agency.Patrick Butlin - 2024 - Mind and Language 39 (1):22-38.
罰を回避する合理的政策の学習.坪井 創吾 宮崎 和光 - 2001 - Transactions of the Japanese Society for Artificial Intelligence 16 (2):185-192.
経験に固執しない Profit Sharing 法.Ueno Atsushi Uemura Wataru - 2006 - Transactions of the Japanese Society for Artificial Intelligence 21:81-93.

Analytics

Added to PP
2022-01-05

Downloads
25 (#753,107)

6 months
4 (#1,151,070)

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