Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034608738> ?p ?o ?g. }
- W3034608738 abstract "We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard constraints (knapsacks). Most of the previous work in constrained reinforcement learning is limited to linear constraints, and the remaining work focuses on either the feasibility question or settings with a single episode. Our experiments demonstrate that the proposed algorithm significantly outperforms these approaches in existing constrained episodic environments." @default.
- W3034608738 created "2020-06-19" @default.
- W3034608738 creator A5022968100 @default.
- W3034608738 creator A5027393001 @default.
- W3034608738 creator A5032266950 @default.
- W3034608738 creator A5037154191 @default.
- W3034608738 creator A5058550942 @default.
- W3034608738 creator A5089372170 @default.
- W3034608738 creator A5091288542 @default.
- W3034608738 date "2020-06-09" @default.
- W3034608738 modified "2023-09-27" @default.
- W3034608738 title "Constrained episodic reinforcement learning in concave-convex and knapsack settings" @default.
- W3034608738 cites W1518931405 @default.
- W3034608738 cites W1570963478 @default.
- W3034608738 cites W1771410628 @default.
- W3034608738 cites W1850488217 @default.
- W3034608738 cites W1980035368 @default.
- W3034608738 cites W2029241234 @default.
- W3034608738 cites W2068490100 @default.
- W3034608738 cites W2076337359 @default.
- W3034608738 cites W2098774185 @default.
- W3034608738 cites W2111957769 @default.
- W3034608738 cites W2113023245 @default.
- W3034608738 cites W2119567691 @default.
- W3034608738 cites W2121863487 @default.
- W3034608738 cites W2145339207 @default.
- W3034608738 cites W2148825261 @default.
- W3034608738 cites W2489939061 @default.
- W3034608738 cites W2546571074 @default.
- W3034608738 cites W2768908787 @default.
- W3034608738 cites W2790607499 @default.
- W3034608738 cites W2915306724 @default.
- W3034608738 cites W2943357710 @default.
- W3034608738 cites W2946284958 @default.
- W3034608738 cites W2949696506 @default.
- W3034608738 cites W2962734844 @default.
- W3034608738 cites W2962803570 @default.
- W3034608738 cites W2963582321 @default.
- W3034608738 cites W2964043796 @default.
- W3034608738 cites W2964054583 @default.
- W3034608738 cites W2964222567 @default.
- W3034608738 cites W2970749192 @default.
- W3034608738 cites W2985924367 @default.
- W3034608738 cites W2990118529 @default.
- W3034608738 cites W3001756029 @default.
- W3034608738 cites W3007236068 @default.
- W3034608738 cites W3008910712 @default.
- W3034608738 cites W3009922106 @default.
- W3034608738 cites W3046395471 @default.
- W3034608738 cites W3121427432 @default.
- W3034608738 cites W3122984617 @default.
- W3034608738 cites W3128962298 @default.
- W3034608738 hasPublicationYear "2020" @default.
- W3034608738 type Work @default.
- W3034608738 sameAs 3034608738 @default.
- W3034608738 citedByCount "9" @default.
- W3034608738 countsByYear W30346087382020 @default.
- W3034608738 countsByYear W30346087382021 @default.
- W3034608738 countsByYear W30346087382022 @default.
- W3034608738 crossrefType "posted-content" @default.
- W3034608738 hasAuthorship W3034608738A5022968100 @default.
- W3034608738 hasAuthorship W3034608738A5027393001 @default.
- W3034608738 hasAuthorship W3034608738A5032266950 @default.
- W3034608738 hasAuthorship W3034608738A5037154191 @default.
- W3034608738 hasAuthorship W3034608738A5058550942 @default.
- W3034608738 hasAuthorship W3034608738A5089372170 @default.
- W3034608738 hasAuthorship W3034608738A5091288542 @default.
- W3034608738 hasConcept C101468663 @default.
- W3034608738 hasConcept C111919701 @default.
- W3034608738 hasConcept C112680207 @default.
- W3034608738 hasConcept C113138325 @default.
- W3034608738 hasConcept C11413529 @default.
- W3034608738 hasConcept C126255220 @default.
- W3034608738 hasConcept C127413603 @default.
- W3034608738 hasConcept C154945302 @default.
- W3034608738 hasConcept C18762648 @default.
- W3034608738 hasConcept C2524010 @default.
- W3034608738 hasConcept C33923547 @default.
- W3034608738 hasConcept C41008148 @default.
- W3034608738 hasConcept C66938386 @default.
- W3034608738 hasConcept C67203356 @default.
- W3034608738 hasConcept C78519656 @default.
- W3034608738 hasConcept C97541855 @default.
- W3034608738 hasConceptScore W3034608738C101468663 @default.
- W3034608738 hasConceptScore W3034608738C111919701 @default.
- W3034608738 hasConceptScore W3034608738C112680207 @default.
- W3034608738 hasConceptScore W3034608738C113138325 @default.
- W3034608738 hasConceptScore W3034608738C11413529 @default.
- W3034608738 hasConceptScore W3034608738C126255220 @default.
- W3034608738 hasConceptScore W3034608738C127413603 @default.
- W3034608738 hasConceptScore W3034608738C154945302 @default.
- W3034608738 hasConceptScore W3034608738C18762648 @default.
- W3034608738 hasConceptScore W3034608738C2524010 @default.
- W3034608738 hasConceptScore W3034608738C33923547 @default.
- W3034608738 hasConceptScore W3034608738C41008148 @default.
- W3034608738 hasConceptScore W3034608738C66938386 @default.
- W3034608738 hasConceptScore W3034608738C67203356 @default.
- W3034608738 hasConceptScore W3034608738C78519656 @default.
- W3034608738 hasConceptScore W3034608738C97541855 @default.
- W3034608738 hasLocation W30346087381 @default.