Loading patent…
AssigneeSony Group Corporation
InventorsDustin Morrill, Thomas J. Walsh, Daniel Hernandez
Estimating the term…
Modern reinforcement learning systems produce many high-quality policies throughout the learning process. However, to choose which policy to actually deploy in the real world, they must be tested under an intractable number of environmental conditions. A process, called Robust Population Optimization for a Small Set of Test cases (“RPOSST”), can select a small set of test cases from a larger pool based on a relatively small number of sample evaluations. RPOSST can treat the test case selection problem as a two-player game and can optimize a solution with provable k-of-N robustness, bounding the error relative to a test that used all the test cases in the pool. Empirical results demonstrate that RPOSST finds a small set of test cases that identify high quality policies in a toy one-shot game, poker datasets, and a high-fidelity racing simulator.
A computer-implemented method for determining a subset of test cases, selected from a set of test cases, that identify candidate deployment policies from a set of policies, comprising:
A method for selecting policies to use in a racing simulation, comprising:
A computer-implemented method for identifying candidate deployment policies from a set of policies, comprising:
Dependencies are inferred from the claim text.