Efficient off-policy credit assignment
US11580445B2 · kind B2 · utility
0Cited by
3References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Oct 15, 2019 |
| Grant date | Feb 14, 2023 |
| Priority date | — |
| Expiry date | Jun 15, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods are provided for efficient off-policy credit assignment (ECA) in reinforcement learning. ECA allows principled credit assignment for off-policy samples, and therefore improves sample efficiency and asymptotic performance. One aspect of ECA is to formulate the optimization of expected return as approximate inference, where policy is approximating a learned prior distribution, which leads to a principled way of utilizing off-policy samples. Other features are also provided.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.