Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897086622> ?p ?o ?g. }
- W2897086622 abstract "We propose an efficient multi-agent reinforcement learning approach to derive equilibrium strategies for multi-agents who are participating in a Markov game. Mainly, we are focused on obtaining decentralized policies for agents to maximize the performance of a collaborative task by all the agents, which is similar to solving a decentralized Markov decision process. We propose to use two different policy networks: (1) decentralized greedy policy network used to generate greedy action during training and execution period and (2) generative cooperative policy network (GCPN) used to generate action samples to make other agents improve their objectives during training period. We show that the samples generated by GCPN enable other agents to explore the policy space more effectively and favorably to reach a better policy in terms of achieving the collaborative tasks." @default.
- W2897086622 created "2018-10-26" @default.
- W2897086622 creator A5023509025 @default.
- W2897086622 creator A5059589497 @default.
- W2897086622 creator A5064587334 @default.
- W2897086622 date "2018-10-22" @default.
- W2897086622 modified "2023-09-27" @default.
- W2897086622 title "Multi-Agent Actor-Critic with Generative Cooperative Policy Network." @default.
- W2897086622 cites W1513468570 @default.
- W2897086622 cites W2012812921 @default.
- W2897086622 cites W2122763142 @default.
- W2897086622 cites W2164637474 @default.
- W2897086622 cites W2173248099 @default.
- W2897086622 cites W2292533394 @default.
- W2897086622 cites W2312609093 @default.
- W2897086622 cites W2617547828 @default.
- W2897086622 cites W2766447205 @default.
- W2897086622 cites W2788115019 @default.
- W2897086622 hasPublicationYear "2018" @default.
- W2897086622 type Work @default.
- W2897086622 sameAs 2897086622 @default.
- W2897086622 citedByCount "2" @default.
- W2897086622 countsByYear W28970866222020 @default.
- W2897086622 countsByYear W28970866222021 @default.
- W2897086622 crossrefType "posted-content" @default.
- W2897086622 hasAuthorship W2897086622A5023509025 @default.
- W2897086622 hasAuthorship W2897086622A5059589497 @default.
- W2897086622 hasAuthorship W2897086622A5064587334 @default.
- W2897086622 hasConcept C105795698 @default.
- W2897086622 hasConcept C106189395 @default.
- W2897086622 hasConcept C111919701 @default.
- W2897086622 hasConcept C119857082 @default.
- W2897086622 hasConcept C120314980 @default.
- W2897086622 hasConcept C121332964 @default.
- W2897086622 hasConcept C126255220 @default.
- W2897086622 hasConcept C154945302 @default.
- W2897086622 hasConcept C159886148 @default.
- W2897086622 hasConcept C162324750 @default.
- W2897086622 hasConcept C175444787 @default.
- W2897086622 hasConcept C187736073 @default.
- W2897086622 hasConcept C22171661 @default.
- W2897086622 hasConcept C2779436431 @default.
- W2897086622 hasConcept C2780451532 @default.
- W2897086622 hasConcept C2780791683 @default.
- W2897086622 hasConcept C33923547 @default.
- W2897086622 hasConcept C39890363 @default.
- W2897086622 hasConcept C41008148 @default.
- W2897086622 hasConcept C42475967 @default.
- W2897086622 hasConcept C62520636 @default.
- W2897086622 hasConcept C97541855 @default.
- W2897086622 hasConcept C98045186 @default.
- W2897086622 hasConcept C98763669 @default.
- W2897086622 hasConceptScore W2897086622C105795698 @default.
- W2897086622 hasConceptScore W2897086622C106189395 @default.
- W2897086622 hasConceptScore W2897086622C111919701 @default.
- W2897086622 hasConceptScore W2897086622C119857082 @default.
- W2897086622 hasConceptScore W2897086622C120314980 @default.
- W2897086622 hasConceptScore W2897086622C121332964 @default.
- W2897086622 hasConceptScore W2897086622C126255220 @default.
- W2897086622 hasConceptScore W2897086622C154945302 @default.
- W2897086622 hasConceptScore W2897086622C159886148 @default.
- W2897086622 hasConceptScore W2897086622C162324750 @default.
- W2897086622 hasConceptScore W2897086622C175444787 @default.
- W2897086622 hasConceptScore W2897086622C187736073 @default.
- W2897086622 hasConceptScore W2897086622C22171661 @default.
- W2897086622 hasConceptScore W2897086622C2779436431 @default.
- W2897086622 hasConceptScore W2897086622C2780451532 @default.
- W2897086622 hasConceptScore W2897086622C2780791683 @default.
- W2897086622 hasConceptScore W2897086622C33923547 @default.
- W2897086622 hasConceptScore W2897086622C39890363 @default.
- W2897086622 hasConceptScore W2897086622C41008148 @default.
- W2897086622 hasConceptScore W2897086622C42475967 @default.
- W2897086622 hasConceptScore W2897086622C62520636 @default.
- W2897086622 hasConceptScore W2897086622C97541855 @default.
- W2897086622 hasConceptScore W2897086622C98045186 @default.
- W2897086622 hasConceptScore W2897086622C98763669 @default.
- W2897086622 hasLocation W28970866221 @default.
- W2897086622 hasOpenAccess W2897086622 @default.
- W2897086622 hasPrimaryLocation W28970866221 @default.
- W2897086622 hasRelatedWork W1542495574 @default.
- W2897086622 hasRelatedWork W1579087965 @default.
- W2897086622 hasRelatedWork W1977595419 @default.
- W2897086622 hasRelatedWork W1998314019 @default.
- W2897086622 hasRelatedWork W2025406794 @default.
- W2897086622 hasRelatedWork W2127638341 @default.
- W2897086622 hasRelatedWork W2161966858 @default.
- W2897086622 hasRelatedWork W2569013745 @default.
- W2897086622 hasRelatedWork W2775322888 @default.
- W2897086622 hasRelatedWork W2797234205 @default.
- W2897086622 hasRelatedWork W2890587089 @default.
- W2897086622 hasRelatedWork W2962938168 @default.
- W2897086622 hasRelatedWork W2995061808 @default.
- W2897086622 hasRelatedWork W2995874959 @default.
- W2897086622 hasRelatedWork W3002908178 @default.
- W2897086622 hasRelatedWork W3005746415 @default.
- W2897086622 hasRelatedWork W3037540495 @default.
- W2897086622 hasRelatedWork W3204697190 @default.
- W2897086622 hasRelatedWork W640950727 @default.
- W2897086622 hasRelatedWork W1579869251 @default.
- W2897086622 isParatext "false" @default.