http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108921298-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-063 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2018-06-12^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-04-19^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-04-19^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108921298-B |
| titleOfInvention | Reinforcement learning for multi-agent communication and decision-making |
| abstract | The invention discloses a multi-agent communication and decision-making method for reinforcement learning, comprising: extracting corresponding state features through a neural network according to the observation state information of each agent; Perform soft allocation and clustering to obtain the clustered communication information; distribute the clustered communication information to each agent, and each agent aggregates its own state characteristics with the received clustered communication information. Action decisions are made through a fully connected neural network inside the agent. This method can cluster the state information of each agent and communicate with other agents, thereby improving the agent's decision-making level. |
| priorityDate | 2018-06-12^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID2950 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419481012 |
Showing number of triples: 1 to 15 of 15.