Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169315127> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3169315127 endingPage "12176" @default.
- W3169315127 startingPage "12167" @default.
- W3169315127 abstract "We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell's approachability theorem (Blackwell, 1956) to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell's approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal." @default.
- W3169315127 created "2021-06-22" @default.
- W3169315127 creator A5004234221 @default.
- W3169315127 creator A5058767558 @default.
- W3169315127 creator A5064766573 @default.
- W3169315127 creator A5075136358 @default.
- W3169315127 date "2021-07-18" @default.
- W3169315127 modified "2023-09-23" @default.
- W3169315127 title "Provably Efficient Algorithms for Multi-Objective Competitive RL" @default.
- W3169315127 hasPublicationYear "2021" @default.
- W3169315127 type Work @default.
- W3169315127 sameAs 3169315127 @default.
- W3169315127 citedByCount "1" @default.
- W3169315127 countsByYear W31693151272021 @default.
- W3169315127 crossrefType "proceedings-article" @default.
- W3169315127 hasAuthorship W3169315127A5004234221 @default.
- W3169315127 hasAuthorship W3169315127A5058767558 @default.
- W3169315127 hasAuthorship W3169315127A5064766573 @default.
- W3169315127 hasAuthorship W3169315127A5075136358 @default.
- W3169315127 hasConcept C105795698 @default.
- W3169315127 hasConcept C106189395 @default.
- W3169315127 hasConcept C11413529 @default.
- W3169315127 hasConcept C119857082 @default.
- W3169315127 hasConcept C126255220 @default.
- W3169315127 hasConcept C14036430 @default.
- W3169315127 hasConcept C154945302 @default.
- W3169315127 hasConcept C159886148 @default.
- W3169315127 hasConcept C177264268 @default.
- W3169315127 hasConcept C199360897 @default.
- W3169315127 hasConcept C2524010 @default.
- W3169315127 hasConcept C33923547 @default.
- W3169315127 hasConcept C41008148 @default.
- W3169315127 hasConcept C57691317 @default.
- W3169315127 hasConcept C78458016 @default.
- W3169315127 hasConcept C86803240 @default.
- W3169315127 hasConcept C97541855 @default.
- W3169315127 hasConcept C98763669 @default.
- W3169315127 hasConceptScore W3169315127C105795698 @default.
- W3169315127 hasConceptScore W3169315127C106189395 @default.
- W3169315127 hasConceptScore W3169315127C11413529 @default.
- W3169315127 hasConceptScore W3169315127C119857082 @default.
- W3169315127 hasConceptScore W3169315127C126255220 @default.
- W3169315127 hasConceptScore W3169315127C14036430 @default.
- W3169315127 hasConceptScore W3169315127C154945302 @default.
- W3169315127 hasConceptScore W3169315127C159886148 @default.
- W3169315127 hasConceptScore W3169315127C177264268 @default.
- W3169315127 hasConceptScore W3169315127C199360897 @default.
- W3169315127 hasConceptScore W3169315127C2524010 @default.
- W3169315127 hasConceptScore W3169315127C33923547 @default.
- W3169315127 hasConceptScore W3169315127C41008148 @default.
- W3169315127 hasConceptScore W3169315127C57691317 @default.
- W3169315127 hasConceptScore W3169315127C78458016 @default.
- W3169315127 hasConceptScore W3169315127C86803240 @default.
- W3169315127 hasConceptScore W3169315127C97541855 @default.
- W3169315127 hasConceptScore W3169315127C98763669 @default.
- W3169315127 hasOpenAccess W3169315127 @default.
- W3169315127 hasRelatedWork W1551424636 @default.
- W3169315127 hasRelatedWork W2479049856 @default.
- W3169315127 hasRelatedWork W2481147314 @default.
- W3169315127 hasRelatedWork W2575682651 @default.
- W3169315127 hasRelatedWork W2902298341 @default.
- W3169315127 hasRelatedWork W2914702425 @default.
- W3169315127 hasRelatedWork W2963215512 @default.
- W3169315127 hasRelatedWork W2991391803 @default.
- W3169315127 hasRelatedWork W3006608344 @default.
- W3169315127 hasRelatedWork W3008953696 @default.
- W3169315127 hasRelatedWork W3038554660 @default.
- W3169315127 hasRelatedWork W3094238158 @default.
- W3169315127 hasRelatedWork W3106398159 @default.
- W3169315127 hasRelatedWork W3126333581 @default.
- W3169315127 hasRelatedWork W3128440853 @default.
- W3169315127 hasRelatedWork W3138269902 @default.
- W3169315127 hasRelatedWork W3177055474 @default.
- W3169315127 hasRelatedWork W3202898482 @default.
- W3169315127 hasRelatedWork W3208476662 @default.
- W3169315127 hasRelatedWork W66477950 @default.
- W3169315127 isParatext "false" @default.
- W3169315127 isRetracted "false" @default.
- W3169315127 magId "3169315127" @default.
- W3169315127 workType "article" @default.