Method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning
US12423383B2 · kind B2 · utility
0Cited by
4References
12Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 6, 2022 |
| Grant date | Sep 23, 2025 |
| Priority date | — |
| Expiry date | Jul 26, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/254
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Provided is a method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning, the method including the steps of: calculating a similarity between a policy of a first agent and a policy of a second agent and computing a final reward using the similarity; and performing clustering on a replay buffer using a result of calculating the similarity between the policy of the first agent and the policy of the second agent and performing sampling on data in the cluster.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.