Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Deterministic limit of temporal difference reinforcement learning for stochastic games
Stockholms universitet, Naturvetenskapliga fakulteten, Stockholm Resilience Centre. Potsdam Institute for Climate Impact Research, Germany.
Rekke forfattare: 32019 (engelsk)Inngår i: Physical review. E, ISSN 2470-0045, E-ISSN 2470-0053, Vol. 99, nr 4, artikkel-id 043305Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Reinforcement learning in multiagent systems has been studied in the fields of economic game theory, artificial intelligence, and statistical physics by developing an analytical understanding of the learning dynamics (often in relation to the replicator dynamics of evolutionary game theory). However, the majority of these analytical studies focuses on repeated normal form games, which only have a single environmental state. Environmental dynamics, i.e., changes in the state of an environment affecting the agents' payoffs has received less attention, lacking a universal method to obtain deterministic equations from established multistate reinforcement learning algorithms. In this work we present a methodological extension, separating the interaction from the adaptation timescale, to derive the deterministic limit of a general class of reinforcement learning algorithms, called temporal difference learning. This form of learning is equipped to function in more realistic multistate environments by using the estimated value of future environmental states to adapt the agent's behavior. We demonstrate the potential of our method with the three well-established learning algorithms Q learning, SARSA learning, and actor-critic learning. Illustrations of their dynamics on two multiagent, multistate environments reveal a wide range of different dynamical regimes, such as convergence to fixed points, limit cycles, and even deterministic chaos.

sted, utgiver, år, opplag, sider
2019. Vol. 99, nr 4, artikkel-id 043305
HSV kategori
Identifikatorer
URN: urn:nbn:se:su:diva-168337DOI: 10.1103/PhysRevE.99.043305ISI: 000464747500007OAI: oai:DiVA.org:su-168337DiVA, id: diva2:1315369
Tilgjengelig fra: 2019-05-13 Laget: 2019-05-13 Sist oppdatert: 2019-05-13bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekst

Søk i DiVA

Av forfatter/redaktør
Donges, Jonathan F.
Av organisasjonen
I samme tidsskrift
Physical review. E

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 3 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf