Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949226350> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W2949226350 abstract "We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions." @default.
- W2949226350 created "2019-06-27" @default.
- W2949226350 creator A5064627349 @default.
- W2949226350 creator A5073944062 @default.
- W2949226350 date "2008-01-01" @default.
- W2949226350 modified "2023-09-24" @default.
- W2949226350 title "On the Possibility of Learning in Reactive Environments with Arbitrary Dependence" @default.
- W2949226350 cites W109120279 @default.
- W2949226350 cites W1505937442 @default.
- W2949226350 cites W1616023682 @default.
- W2949226350 cites W166089536 @default.
- W2949226350 cites W171065245 @default.
- W2949226350 cites W1913459642 @default.
- W2949226350 cites W2112223472 @default.
- W2949226350 cites W2121863487 @default.
- W2949226350 cites W2154658964 @default.
- W2949226350 cites W2799137445 @default.
- W2949226350 cites W2949185669 @default.
- W2949226350 cites W2949618782 @default.
- W2949226350 cites W2951970805 @default.
- W2949226350 hasPublicationYear "2008" @default.
- W2949226350 type Work @default.
- W2949226350 sameAs 2949226350 @default.
- W2949226350 citedByCount "0" @default.
- W2949226350 crossrefType "journal-article" @default.
- W2949226350 hasAuthorship W2949226350A5064627349 @default.
- W2949226350 hasAuthorship W2949226350A5073944062 @default.
- W2949226350 hasBestOaLocation W29492263502 @default.
- W2949226350 hasConcept C15744967 @default.
- W2949226350 hasConcept C161790260 @default.
- W2949226350 hasConcept C185592680 @default.
- W2949226350 hasConcept C192937433 @default.
- W2949226350 hasConcept C41008148 @default.
- W2949226350 hasConcept C55493867 @default.
- W2949226350 hasConceptScore W2949226350C15744967 @default.
- W2949226350 hasConceptScore W2949226350C161790260 @default.
- W2949226350 hasConceptScore W2949226350C185592680 @default.
- W2949226350 hasConceptScore W2949226350C192937433 @default.
- W2949226350 hasConceptScore W2949226350C41008148 @default.
- W2949226350 hasConceptScore W2949226350C55493867 @default.
- W2949226350 hasLocation W29492263501 @default.
- W2949226350 hasLocation W29492263502 @default.
- W2949226350 hasLocation W29492263503 @default.
- W2949226350 hasOpenAccess W2949226350 @default.
- W2949226350 hasPrimaryLocation W29492263501 @default.
- W2949226350 hasRelatedWork W2093578348 @default.
- W2949226350 hasRelatedWork W2350741829 @default.
- W2949226350 hasRelatedWork W2358668433 @default.
- W2949226350 hasRelatedWork W2376932109 @default.
- W2949226350 hasRelatedWork W2382290278 @default.
- W2949226350 hasRelatedWork W2390279801 @default.
- W2949226350 hasRelatedWork W2748952813 @default.
- W2949226350 hasRelatedWork W2766271392 @default.
- W2949226350 hasRelatedWork W2899084033 @default.
- W2949226350 hasRelatedWork W562660023 @default.
- W2949226350 isParatext "false" @default.
- W2949226350 isRetracted "false" @default.
- W2949226350 magId "2949226350" @default.
- W2949226350 workType "article" @default.