Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119642227> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3119642227 abstract "In this work, we consider the problem of computing optimal actions for Reinforcement Learning (RL) agents in a co-operative setting, where the objective is to optimize a common goal. However, in many real-life applications, in addition to optimizing the goal, the agents are required to satisfy certain constraints specified on their actions. Under this setting, the objective of the agents is to not only learn the actions that optimize the common objective but also meet the specified constraints. In recent times, the Actor-Critic algorithm with an attention mechanism has been successfully applied to obtain optimal actions for RL agents in multi-agent environments. In this work, we extend this algorithm to the constrained multi-agent RL setting. The idea here is that optimizing the common goal and satisfying the constraints may require different modes of attention. By incorporating different attention modes, the agents can select useful information required for optimizing the objective and satisfying the constraints separately, thereby yielding better actions. Through experiments on benchmark multi-agent environments, we show the effectiveness of our proposed algorithm." @default.
- W3119642227 created "2021-01-18" @default.
- W3119642227 creator A5002033038 @default.
- W3119642227 creator A5025933471 @default.
- W3119642227 creator A5036342763 @default.
- W3119642227 creator A5038163398 @default.
- W3119642227 date "2021-01-07" @default.
- W3119642227 modified "2023-09-27" @default.
- W3119642227 title "Attention Actor-Critic algorithm for Multi-Agent Constrained Co-operative Reinforcement Learning" @default.
- W3119642227 cites W1514535095 @default.
- W3119642227 cites W2070410573 @default.
- W3119642227 cites W2070570138 @default.
- W3119642227 cites W2073314543 @default.
- W3119642227 cites W2094364653 @default.
- W3119642227 cites W2099618002 @default.
- W3119642227 cites W2121863487 @default.
- W3119642227 cites W2156162802 @default.
- W3119642227 cites W2161270100 @default.
- W3119642227 cites W2396906324 @default.
- W3119642227 cites W2530849036 @default.
- W3119642227 cites W2574190180 @default.
- W3119642227 cites W2577958246 @default.
- W3119642227 cites W2616964725 @default.
- W3119642227 cites W2617547828 @default.
- W3119642227 cites W2781726626 @default.
- W3119642227 cites W2788014517 @default.
- W3119642227 cites W2804791273 @default.
- W3119642227 cites W2889870232 @default.
- W3119642227 cites W2908261578 @default.
- W3119642227 cites W2944412600 @default.
- W3119642227 cites W2945449812 @default.
- W3119642227 cites W2951303605 @default.
- W3119642227 cites W2962966033 @default.
- W3119642227 cites W2963407617 @default.
- W3119642227 cites W2963562809 @default.
- W3119642227 cites W2963658727 @default.
- W3119642227 cites W2963717208 @default.
- W3119642227 cites W2968526727 @default.
- W3119642227 cites W3037540495 @default.
- W3119642227 cites W3148322241 @default.
- W3119642227 hasPublicationYear "2021" @default.
- W3119642227 type Work @default.
- W3119642227 sameAs 3119642227 @default.
- W3119642227 citedByCount "1" @default.
- W3119642227 countsByYear W31196422272021 @default.
- W3119642227 crossrefType "posted-content" @default.
- W3119642227 hasAuthorship W3119642227A5002033038 @default.
- W3119642227 hasAuthorship W3119642227A5025933471 @default.
- W3119642227 hasAuthorship W3119642227A5036342763 @default.
- W3119642227 hasAuthorship W3119642227A5038163398 @default.
- W3119642227 hasConcept C126255220 @default.
- W3119642227 hasConcept C13280743 @default.
- W3119642227 hasConcept C154945302 @default.
- W3119642227 hasConcept C185798385 @default.
- W3119642227 hasConcept C205649164 @default.
- W3119642227 hasConcept C33923547 @default.
- W3119642227 hasConcept C41008148 @default.
- W3119642227 hasConcept C97541855 @default.
- W3119642227 hasConceptScore W3119642227C126255220 @default.
- W3119642227 hasConceptScore W3119642227C13280743 @default.
- W3119642227 hasConceptScore W3119642227C154945302 @default.
- W3119642227 hasConceptScore W3119642227C185798385 @default.
- W3119642227 hasConceptScore W3119642227C205649164 @default.
- W3119642227 hasConceptScore W3119642227C33923547 @default.
- W3119642227 hasConceptScore W3119642227C41008148 @default.
- W3119642227 hasConceptScore W3119642227C97541855 @default.
- W3119642227 hasLocation W31196422271 @default.
- W3119642227 hasOpenAccess W3119642227 @default.
- W3119642227 hasPrimaryLocation W31196422271 @default.
- W3119642227 hasRelatedWork W1534566263 @default.
- W3119642227 hasRelatedWork W1818607911 @default.
- W3119642227 hasRelatedWork W2120386704 @default.
- W3119642227 hasRelatedWork W2259575993 @default.
- W3119642227 hasRelatedWork W2609855605 @default.
- W3119642227 hasRelatedWork W2937587379 @default.
- W3119642227 hasRelatedWork W2940740707 @default.
- W3119642227 hasRelatedWork W2944412600 @default.
- W3119642227 hasRelatedWork W2971604276 @default.
- W3119642227 hasRelatedWork W2996527614 @default.
- W3119642227 hasRelatedWork W3003470745 @default.
- W3119642227 hasRelatedWork W3009759305 @default.
- W3119642227 hasRelatedWork W3110570238 @default.
- W3119642227 hasRelatedWork W3133981671 @default.
- W3119642227 hasRelatedWork W3158051401 @default.
- W3119642227 hasRelatedWork W3173294282 @default.
- W3119642227 hasRelatedWork W3174374257 @default.
- W3119642227 hasRelatedWork W3174543778 @default.
- W3119642227 hasRelatedWork W3209477841 @default.
- W3119642227 hasRelatedWork W3097040155 @default.
- W3119642227 isParatext "false" @default.
- W3119642227 isRetracted "false" @default.
- W3119642227 magId "3119642227" @default.
- W3119642227 workType "article" @default.