Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat 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.
Antal upphovsmän: 32019 (Engelska)Ingår i: Physical review. E, ISSN 2470-0045, E-ISSN 2470-0053, Vol. 99, nr 4, artikel-id 043305Artikel i tidskrift (Refereegranskat) 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.

Ort, förlag, år, upplaga, sidor
2019. Vol. 99, nr 4, artikel-id 043305
Nationell ämneskategori
Fysik Matematik
Identifikatorer
URN: urn:nbn:se:su:diva-168337DOI: 10.1103/PhysRevE.99.043305ISI: 000464747500007OAI: oai:DiVA.org:su-168337DiVA, id: diva2:1315369
Tillgänglig från: 2019-05-13 Skapad: 2019-05-13 Senast uppdaterad: 2019-05-13Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Sök vidare i DiVA

Av författaren/redaktören
Donges, Jonathan F.
Av organisationen
Stockholm Resilience Centre
I samma tidskrift
Physical review. E
FysikMatematik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 2 träffar
RefereraExporteraLänk till posten
Permanent länk

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