Understanding reinforcement learning policies by identifying strategic states
AssigneeInternational Business Machines Corporation
InventorsRonny Luss, Amit Dhurandhar, MIAO LIU
Life of this patent
Estimating the term…
Abstract
One or more computer processors compute a maximum likelihood path matrix comprising a respective shortest path between each state in a set of states associated with a model trained with a deep reinforcement learning policy. The one or more computer processors generate explanations for the deep reinforcement learning policy based one or more identified meta-states for each state in the set of states and corresponding selected strategic states utilizing the computed maximum likelihood path matrix.
Claims20
A computer-implemented method comprising:
- computing, by one or more computer processors, a maximum likelihood path matrix comprising a respective shortest path between each state in a set of states associated with a model trained with a deep reinforcement learning policy;
- and
- generating, by one or more computer processors, explanations for the deep reinforcement learning policy based one or more identified meta-states for each state in the set of states and corresponding selected strategic states utilizing the computed maximum likelihood path matrix.
A computer program product comprising:
- one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising:
- program instructions to compute a maximum likelihood path matrix comprising a respective shortest path between each state in a set of states associated with a model trained with a deep reinforcement learning policy;
- and
- program instructions to generate explanations for the deep reinforcement learning policy based one or more identified meta-states for each state in the set of states and corresponding selected strategic states utilizing the computed maximum likelihood path matrix.
A computer system comprising:
- one or more computer processors;
- one or more computer readable storage media;
- and
- program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the stored program instructions comprising:
- program instructions to compute a maximum likelihood path matrix comprising a respective shortest path between each state in a set of states associated with a model trained with a deep reinforcement learning policy;
- and
- program instructions to generate explanations for the deep reinforcement learning policy based one or more identified meta-states for each state in the set of states and corresponding selected strategic states utilizing the computed maximum likelihood path matrix.
Dependencies are inferred from the claim text.