Self-play to improve task-oriented dialog systems and methods
US12026544B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 25, 2020 |
| Grant date | Jul 2, 2024 |
| Priority date | — |
| Expiry date | Apr 14, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/223
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An automatic agent may be trained using reinforcement learning. A secret task may be obtained for a simulated user, and the secret task may be unknown to the automatic agent. At least one instruction to complete the secret task may be obtained from the simulated user according to at least one RL policy. At least one action may be generated by the automatic agent based on the at least one instruction and the at least one RL policy. Rewards may be determined for the simulated user and the automatic agent in response to determining that the at least one action successfully completes the secret task. The at least one RL policy may be adjusted based on the determined rewards.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.