Accelerated deep reinforcement learning of agent control policies
AssigneeWaymo LLC
InventorsKhaled Refaat, Kai Ding
Life of this patent
Estimating the term…
Loading patent…
AssigneeWaymo LLC
InventorsKhaled Refaat, Kai Ding
Estimating the term…
Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a mixture of a plurality of actor-critic policies that is used to control an agent interacting with an environment to perform a task. Each actor-critic policy includes an actor policy and a critic policy. The training includes, for each of one or more transitions, determining a target Q value for the transition from (i) the reward in the transition, and (ii) an imagined return estimate generated by performing one or more iterations of a prediction process to generate one or more predicted future transitions.
A method for training a mixture of a plurality of actor-critic policies that is used to control an agent interacting with an environment to perform a task, each actor-critic policy comprising:
A system comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform training of a mixture of a plurality of actor-critic policies that is used to control an agent interacting with an environment to perform a task, each actor-critic policy comprising:
A computer storage medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform training of a mixture of a plurality of actor-critic policies that is used to control an agent interacting with an environment to perform a task, each actor-critic policy comprising:
Dependencies are inferred from the claim text.