Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945166833> ?p ?o ?g. }
- W2945166833 endingPage "2266" @default.
- W2945166833 startingPage "2265" @default.
- W2945166833 abstract "Learning to coordinate is a hard task for reinforcement learning due to a game-theoretic pathology known as relative overgeneralization. To help deal with this, we propose two methods which apply forms of imitation learning to the problem of learning coordinated behaviors. The proposed methods have a close connection to multiagent actor-critic models, and will avoid relative overgeneralization if the right demonstrations are given. We compare our algorithms with MADDPG, a state-of-the-art approach, and show that our methods achieve better coordination in multiagent cooperative tasks." @default.
- W2945166833 created "2019-05-29" @default.
- W2945166833 creator A5049459954 @default.
- W2945166833 creator A5050387520 @default.
- W2945166833 creator A5060013477 @default.
- W2945166833 date "2019-05-08" @default.
- W2945166833 modified "2023-09-23" @default.
- W2945166833 title "Multiagent Adversarial Inverse Reinforcement Learning" @default.
- W2945166833 cites W156814138 @default.
- W2945166833 cites W1590759229 @default.
- W2945166833 cites W1744420786 @default.
- W2945166833 cites W1771410628 @default.
- W2945166833 cites W1999874108 @default.
- W2945166833 cites W2065821056 @default.
- W2945166833 cites W2095865381 @default.
- W2945166833 cites W2099471712 @default.
- W2945166833 cites W2124394479 @default.
- W2945166833 cites W2129936995 @default.
- W2945166833 cites W2155027007 @default.
- W2945166833 cites W2162262334 @default.
- W2945166833 cites W2165150801 @default.
- W2945166833 cites W2173248099 @default.
- W2945166833 cites W2173520492 @default.
- W2945166833 cites W2401592218 @default.
- W2945166833 cites W2466211196 @default.
- W2945166833 cites W2527819024 @default.
- W2945166833 cites W2566467060 @default.
- W2945166833 cites W2594103415 @default.
- W2945166833 cites W2740210681 @default.
- W2945166833 cites W2798511001 @default.
- W2945166833 cites W2799151646 @default.
- W2945166833 cites W2949201811 @default.
- W2945166833 cites W2950465931 @default.
- W2945166833 cites W2951896791 @default.
- W2945166833 cites W2962793481 @default.
- W2945166833 cites W2962938168 @default.
- W2945166833 cites W2963000099 @default.
- W2945166833 cites W2963277051 @default.
- W2945166833 cites W2963485523 @default.
- W2945166833 cites W2963508354 @default.
- W2945166833 cites W2963590100 @default.
- W2945166833 cites W2963797805 @default.
- W2945166833 hasPublicationYear "2019" @default.
- W2945166833 type Work @default.
- W2945166833 sameAs 2945166833 @default.
- W2945166833 citedByCount "1" @default.
- W2945166833 countsByYear W29451668332020 @default.
- W2945166833 crossrefType "proceedings-article" @default.
- W2945166833 hasAuthorship W2945166833A5049459954 @default.
- W2945166833 hasAuthorship W2945166833A5050387520 @default.
- W2945166833 hasAuthorship W2945166833A5060013477 @default.
- W2945166833 hasConcept C11413529 @default.
- W2945166833 hasConcept C119857082 @default.
- W2945166833 hasConcept C126388530 @default.
- W2945166833 hasConcept C127413603 @default.
- W2945166833 hasConcept C154945302 @default.
- W2945166833 hasConcept C15744967 @default.
- W2945166833 hasConcept C201995342 @default.
- W2945166833 hasConcept C2780451532 @default.
- W2945166833 hasConcept C37736160 @default.
- W2945166833 hasConcept C41008148 @default.
- W2945166833 hasConcept C41550386 @default.
- W2945166833 hasConcept C47932503 @default.
- W2945166833 hasConcept C48103436 @default.
- W2945166833 hasConcept C77805123 @default.
- W2945166833 hasConcept C97541855 @default.
- W2945166833 hasConceptScore W2945166833C11413529 @default.
- W2945166833 hasConceptScore W2945166833C119857082 @default.
- W2945166833 hasConceptScore W2945166833C126388530 @default.
- W2945166833 hasConceptScore W2945166833C127413603 @default.
- W2945166833 hasConceptScore W2945166833C154945302 @default.
- W2945166833 hasConceptScore W2945166833C15744967 @default.
- W2945166833 hasConceptScore W2945166833C201995342 @default.
- W2945166833 hasConceptScore W2945166833C2780451532 @default.
- W2945166833 hasConceptScore W2945166833C37736160 @default.
- W2945166833 hasConceptScore W2945166833C41008148 @default.
- W2945166833 hasConceptScore W2945166833C41550386 @default.
- W2945166833 hasConceptScore W2945166833C47932503 @default.
- W2945166833 hasConceptScore W2945166833C48103436 @default.
- W2945166833 hasConceptScore W2945166833C77805123 @default.
- W2945166833 hasConceptScore W2945166833C97541855 @default.
- W2945166833 hasLocation W29451668331 @default.
- W2945166833 hasOpenAccess W2945166833 @default.
- W2945166833 hasPrimaryLocation W29451668331 @default.
- W2945166833 hasRelatedWork W1489679543 @default.
- W2945166833 hasRelatedWork W1502765764 @default.
- W2945166833 hasRelatedWork W1519098124 @default.
- W2945166833 hasRelatedWork W1546266526 @default.
- W2945166833 hasRelatedWork W1594607371 @default.
- W2945166833 hasRelatedWork W1835254890 @default.
- W2945166833 hasRelatedWork W2008693313 @default.
- W2945166833 hasRelatedWork W2105741987 @default.
- W2945166833 hasRelatedWork W2110231930 @default.
- W2945166833 hasRelatedWork W2141559645 @default.
- W2945166833 hasRelatedWork W2162597815 @default.
- W2945166833 hasRelatedWork W2169792277 @default.
- W2945166833 hasRelatedWork W2946234491 @default.
- W2945166833 hasRelatedWork W2954141457 @default.