Method and system for interactive imitation learning in video games
US11369879B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 18, 2019 |
| Grant date | Jun 28, 2022 |
| Priority date | — |
| Expiry date | Aug 27, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In example embodiments, a method of interactive imitation learning method is disclosed. An input is received from an input device. The input includes data describing a first set of example actions defining a behavior for a virtual character. Inverse reinforcement learning is used to estimate a reward function for the set of example actions. The reward function and the set of example actions is used as input to a reinforcement learning model to train a machine learning agent to mimic the behavior in a training environment. Based on a measure of failure of the training of the machine learning agent reaching a threshold, the training of the machine learning agent is paused to request a second set of example actions from the input device. The second set of example actions is used in addition to the first set of example actions to estimate a new reward function.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.