Estimating the level of inference using an order-mimic agent

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 246
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorJoo, Haramko
dc.contributor.authorJeong, Inhyeokko
dc.contributor.authorLee, Sang Wanko
dc.date.accessioned2022-01-11T06:52:46Z-
dc.date.available2022-01-11T06:52:46Z-
dc.date.created2021-11-30-
dc.date.created2021-11-30-
dc.date.created2021-11-30-
dc.date.issued2021-11-10-
dc.identifier.citationthe 6th Asian Conference on Pattern Recognition (ACPR2021), pp.116 - 126-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10203/291737-
dc.description.abstractMulti-agent reinforcement learning (RL) considers problems of learning policies and predicting values through interactions with multiple opponents. To make the solutions feasible, one assumes single-type opponents. However, this may not hold in most real-world situations. Interactions with a mixture of different types of agents make it extremely hard to learn. This study examines the hypothesis that when the potential types of agents are unknown, the level of agent inference can act as a proxy for characterizing the opponents. We present a computational framework to estimate the level of agent's inference using a deterministic and stochastic order-mimic agent. We then propose a calibration method for unbiased estimation, which offsets the adverse effect of order-mimic agents on the environment's order estimation. Finally, to generalize the method to a wide range of contexts, we proposed iterative inference level estimation. We demonstrate the feasibility of the proposed method in computer simulations with agents mimicking agents' behavior with various inference levels. Our framework can estimate the learning capacity of various algorithms and humans; therefore it can be used to design high-level inference models that can effectively handle the complexity of multi-agent learning problems.-
dc.languageEnglish-
dc.publisherKorea University Institute for Artificial Intelligence, Korea Brain Education Society-
dc.titleEstimating the level of inference using an order-mimic agent-
dc.typeConference-
dc.identifier.wosid000873422200009-
dc.identifier.scopusid2-s2.0-85130213762-
dc.type.rimsCONF-
dc.citation.beginningpage116-
dc.citation.endingpage126-
dc.citation.publicationnamethe 6th Asian Conference on Pattern Recognition (ACPR2021)-
dc.identifier.conferencecountryKO-
dc.identifier.conferencelocationJeju Island-
dc.identifier.doi10.1007/978-3-031-02444-3_9-
dc.contributor.localauthorLee, Sang Wan-
dc.contributor.nonIdAuthorJoo, Haram-
dc.contributor.nonIdAuthorJeong, Inhyeok-
Appears in Collection
BC-Conference Papers(학술대회논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0