Evaluating reinforcement learning policies
US10445653B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 7, 2015 |
| Grant date | Oct 15, 2019 |
| Priority date | — |
| Expiry date | May 20, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/022
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating reinforcement learning policies. One of the methods includes receiving a plurality of training histories for a reinforcement learning agent; determining a total reward for each training observation in the training histories; partitioning the training observations into a plurality of partitions; determining, for each partition and from the partitioned training observations, a probability that the reinforcement learning agent will receive the total reward for the partition if the reinforcement learning agent performs the action for the partition in response to receiving the current observation; determining, from the probabilities and for each total reward, a respective estimated value of performing each action in response to receiving the current observation; and selecting an action from the pre-determined set of actions from the estimated values in accordance with an action selection policy.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.