Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386822106> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4386822106 abstract "Multi-agent reinforcement learning algorithm has been proposed, demonstrated, and improved on tasks which require a team of agents to cooperate or compete to complete. Sometimes the agents are caught in some dilemmas caused by incomplete observation of environmental information, using the existing q-learning algorithms. Thus, our team come up with the idea of introducing an early warning mechanism to tackle this problem. Actor-critic is a special method to achieve early warning mechanism, guiding the actors' follow-up actions through the existence of critic agent. This kind of algorithm is applicable not only in shared rewards settings, but also in individualized settings where the agents are not able to know the global state. Nowadays, it has become a broad consensus to use the game simulation environment as a research and verification environment for artificial intelligence. In this paper, the Snake Game real-time battle platform is selected as the research environment of the multi-agent reinforcement learning algorithm and the performance of the q-learning algorithm and the actor-critic algorithm is compared on the platform. To further improve the actor-critic algorithm, a better way of experience replay is introduced and its performance is also compared in this environment." @default.
- W4386822106 created "2023-09-19" @default.
- W4386822106 creator A5028529375 @default.
- W4386822106 creator A5075598591 @default.
- W4386822106 creator A5080344490 @default.
- W4386822106 creator A5092893121 @default.
- W4386822106 date "2023-07-24" @default.
- W4386822106 modified "2023-09-26" @default.
- W4386822106 title "A Multi-Agent Actor-Critic Based Approach Applied to the Snake Game" @default.
- W4386822106 cites W1542941925 @default.
- W4386822106 cites W2088956500 @default.
- W4386822106 cites W2145339207 @default.
- W4386822106 cites W2602275733 @default.
- W4386822106 cites W2617547828 @default.
- W4386822106 cites W2766447205 @default.
- W4386822106 cites W2963658727 @default.
- W4386822106 cites W3156295478 @default.
- W4386822106 cites W32403112 @default.
- W4386822106 doi "https://doi.org/10.23919/ccc58697.2023.10241182" @default.
- W4386822106 hasPublicationYear "2023" @default.
- W4386822106 type Work @default.
- W4386822106 citedByCount "0" @default.
- W4386822106 crossrefType "proceedings-article" @default.
- W4386822106 hasAuthorship W4386822106A5028529375 @default.
- W4386822106 hasAuthorship W4386822106A5075598591 @default.
- W4386822106 hasAuthorship W4386822106A5080344490 @default.
- W4386822106 hasAuthorship W4386822106A5092893121 @default.
- W4386822106 hasConcept C111472728 @default.
- W4386822106 hasConcept C11413529 @default.
- W4386822106 hasConcept C138885662 @default.
- W4386822106 hasConcept C154945302 @default.
- W4386822106 hasConcept C41008148 @default.
- W4386822106 hasConcept C41550386 @default.
- W4386822106 hasConcept C48103436 @default.
- W4386822106 hasConcept C89611455 @default.
- W4386822106 hasConcept C97541855 @default.
- W4386822106 hasConceptScore W4386822106C111472728 @default.
- W4386822106 hasConceptScore W4386822106C11413529 @default.
- W4386822106 hasConceptScore W4386822106C138885662 @default.
- W4386822106 hasConceptScore W4386822106C154945302 @default.
- W4386822106 hasConceptScore W4386822106C41008148 @default.
- W4386822106 hasConceptScore W4386822106C41550386 @default.
- W4386822106 hasConceptScore W4386822106C48103436 @default.
- W4386822106 hasConceptScore W4386822106C89611455 @default.
- W4386822106 hasConceptScore W4386822106C97541855 @default.
- W4386822106 hasLocation W43868221061 @default.
- W4386822106 hasOpenAccess W4386822106 @default.
- W4386822106 hasPrimaryLocation W43868221061 @default.
- W4386822106 hasRelatedWork W260766989 @default.
- W4386822106 hasRelatedWork W2959276766 @default.
- W4386822106 hasRelatedWork W3022038857 @default.
- W4386822106 hasRelatedWork W3074294383 @default.
- W4386822106 hasRelatedWork W3111983280 @default.
- W4386822106 hasRelatedWork W3139193008 @default.
- W4386822106 hasRelatedWork W3164468573 @default.
- W4386822106 hasRelatedWork W4206669594 @default.
- W4386822106 hasRelatedWork W4295941380 @default.
- W4386822106 hasRelatedWork W4319083788 @default.
- W4386822106 isParatext "false" @default.
- W4386822106 isRetracted "false" @default.
- W4386822106 workType "article" @default.