Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385758895> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4385758895 endingPage "9174" @default.
- W4385758895 startingPage "9174" @default.
- W4385758895 abstract "In this study, we propose an innovative approach to address a chronological planning problem involving the multiple agents required to complete tasks under precedence constraints. We model this problem as a stochastic game and solve it with multi-agent reinforcement learning algorithms. However, these algorithms necessitate relearning from scratch when confronted with changes in the chronological order of tasks, resulting in distinct stochastic games and consuming a substantial amount of time. To overcome this challenge, we present a novel framework that incorporates meta-learning into a multi-agent reinforcement learning algorithm. This approach enables the extraction of meta-parameters from past experiences, facilitating rapid adaptation to new tasks with altered chronological orders and circumventing the time-intensive nature of reinforcement learning. Then, the proposed framework is demonstrated through the implementation of a method named Reptile-MADDPG. The performance of the pre-trained model is evaluated using average rewards before and after fine-tuning. Our method, in two testing tasks, improves the average rewards from −44 to −37 through 10,000 steps of fine-tuning in two testing tasks, significantly surpassing the two baseline methods that only attained −51 and −44, respectively. The experimental results demonstrate the superior generalization capabilities of our method across various tasks, thus constituting a significant contribution towards the design of intelligent unmanned systems." @default.
- W4385758895 created "2023-08-12" @default.
- W4385758895 creator A5005322009 @default.
- W4385758895 creator A5016486530 @default.
- W4385758895 creator A5021596402 @default.
- W4385758895 creator A5058396327 @default.
- W4385758895 creator A5076970762 @default.
- W4385758895 date "2023-08-11" @default.
- W4385758895 modified "2023-10-18" @default.
- W4385758895 title "Multi-Agent Chronological Planning with Model-Agnostic Meta Reinforcement Learning" @default.
- W4385758895 cites W1641379095 @default.
- W4385758895 cites W2089217417 @default.
- W4385758895 cites W2145339207 @default.
- W4385758895 cites W2605102758 @default.
- W4385758895 cites W2979097258 @default.
- W4385758895 cites W2996333549 @default.
- W4385758895 cites W3015206254 @default.
- W4385758895 cites W3016080886 @default.
- W4385758895 cites W3020785977 @default.
- W4385758895 cites W3033672499 @default.
- W4385758895 cites W3083103237 @default.
- W4385758895 cites W3117800719 @default.
- W4385758895 cites W3131239339 @default.
- W4385758895 cites W3136553706 @default.
- W4385758895 cites W3154784371 @default.
- W4385758895 cites W3199468499 @default.
- W4385758895 cites W3203076355 @default.
- W4385758895 cites W3204518412 @default.
- W4385758895 cites W3209453546 @default.
- W4385758895 cites W4281686250 @default.
- W4385758895 cites W4283460176 @default.
- W4385758895 cites W4306160133 @default.
- W4385758895 doi "https://doi.org/10.3390/app13169174" @default.
- W4385758895 hasPublicationYear "2023" @default.
- W4385758895 type Work @default.
- W4385758895 citedByCount "0" @default.
- W4385758895 crossrefType "journal-article" @default.
- W4385758895 hasAuthorship W4385758895A5005322009 @default.
- W4385758895 hasAuthorship W4385758895A5016486530 @default.
- W4385758895 hasAuthorship W4385758895A5021596402 @default.
- W4385758895 hasAuthorship W4385758895A5058396327 @default.
- W4385758895 hasAuthorship W4385758895A5076970762 @default.
- W4385758895 hasBestOaLocation W43857588951 @default.
- W4385758895 hasConcept C119857082 @default.
- W4385758895 hasConcept C120665830 @default.
- W4385758895 hasConcept C121332964 @default.
- W4385758895 hasConcept C127413603 @default.
- W4385758895 hasConcept C134306372 @default.
- W4385758895 hasConcept C139807058 @default.
- W4385758895 hasConcept C154945302 @default.
- W4385758895 hasConcept C177148314 @default.
- W4385758895 hasConcept C201995342 @default.
- W4385758895 hasConcept C2780451532 @default.
- W4385758895 hasConcept C2781002164 @default.
- W4385758895 hasConcept C33923547 @default.
- W4385758895 hasConcept C41008148 @default.
- W4385758895 hasConcept C97541855 @default.
- W4385758895 hasConceptScore W4385758895C119857082 @default.
- W4385758895 hasConceptScore W4385758895C120665830 @default.
- W4385758895 hasConceptScore W4385758895C121332964 @default.
- W4385758895 hasConceptScore W4385758895C127413603 @default.
- W4385758895 hasConceptScore W4385758895C134306372 @default.
- W4385758895 hasConceptScore W4385758895C139807058 @default.
- W4385758895 hasConceptScore W4385758895C154945302 @default.
- W4385758895 hasConceptScore W4385758895C177148314 @default.
- W4385758895 hasConceptScore W4385758895C201995342 @default.
- W4385758895 hasConceptScore W4385758895C2780451532 @default.
- W4385758895 hasConceptScore W4385758895C2781002164 @default.
- W4385758895 hasConceptScore W4385758895C33923547 @default.
- W4385758895 hasConceptScore W4385758895C41008148 @default.
- W4385758895 hasConceptScore W4385758895C97541855 @default.
- W4385758895 hasFunder F4320321001 @default.
- W4385758895 hasIssue "16" @default.
- W4385758895 hasLocation W43857588951 @default.
- W4385758895 hasOpenAccess W4385758895 @default.
- W4385758895 hasPrimaryLocation W43857588951 @default.
- W4385758895 hasRelatedWork W2906917062 @default.
- W4385758895 hasRelatedWork W2979869797 @default.
- W4385758895 hasRelatedWork W3035417664 @default.
- W4385758895 hasRelatedWork W3037114224 @default.
- W4385758895 hasRelatedWork W3161250517 @default.
- W4385758895 hasRelatedWork W3199608561 @default.
- W4385758895 hasRelatedWork W4312903001 @default.
- W4385758895 hasRelatedWork W4319083788 @default.
- W4385758895 hasRelatedWork W4319309271 @default.
- W4385758895 hasRelatedWork W4379251374 @default.
- W4385758895 hasVolume "13" @default.
- W4385758895 isParatext "false" @default.
- W4385758895 isRetracted "false" @default.
- W4385758895 workType "article" @default.