Sony Group Corporation

Sony Corporation of America

University of Michigan

Deepmind Technologies Limited

Satinder Singh Baveja

Peter R Wurman

David Silver

Hado Philip Van Hasselt

James MacGlashan

Mark Ring

Varun Kompella

Emily Mower Provost

Zhongwen Xu

Matteo Hessel

Kaushik Subramanian

Roberto Capobianco

Samuel Barrett

Peter Stone

Melvin Mcinnis

Michael Bowling

Zahi N Karam

Junhyuk Oh

Zeyu Zheng

Iurii Kemaev

Tom Ben Zion Zahavy

A method and system for teaching an artificial intelligent agent where the agent can be placed in a state that it would like it to learn how to achieve. By giving the agent several examples, it can learn to identify what is important about these example states. Once the agent has the ability to recognize a goal configuration, it can use that information to then learn how to achieve the goal states on its own. An agent may be provided with positive and negative examples to demonstrate a goal configuration. Once the agent has learned certain goal configurations, the agent can learn policies and skills that achieve the learned goal configuration. The agent may create a collection of these policies and skills from which to select based on a particular command or state.

Method and system for an intelligent artificial agent

There is described methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. The reinforcement learning system comprises an agent configured to perform actions based upon a policy and an intrinsic reward system configured to generate intrinsic reward values for the agent based upon the actions taken by the agent. The method comprises training the reinforcement learning system based upon a plurality of tasks. The training comprises updating the agent's policy based upon the intrinsic reward values generated by the intrinsic reward system and updating the intrinsic reward system based upon an extrinsic reward value obtained based upon the task being performed by the agent. The training further comprises re-initializing the agent's policy when an expiration criterion associated with the agent is met.

Reinforcement learning using meta-learned intrinsic rewards

Systems and methods use deep, convolutional neural networks over exponentially long history windows to learn alphabets for context tree weighting (CTW) for prediction. Known issues of depth and breadth in conventional context tree weighting predictions are addressed by the systems and methods. To deal with depth, the history can be broken into time windows, permitting the ability to look exponentially far back while having less information the further one looks back. To deal with breadth, a deep neural network classifier can be used to learn to map arbitrary length histories to a small output symbol alphabet. The sequence of symbols produced by such a classifier over the history windows would then become the input sequence to CTW.

Method and system for predicting discrete sequences using deep context tree weighting

A method and system for teaching an artificial intelligent agent includes giving the agent several examples where it can learn to identify what is important about these example states. Once the agent has the ability to recognize a goal configuration, it can use that information to then learn how to achieve the goal states on its own. An agent may be provided with positive and negative examples to demonstrate a goal configuration. Once the agent has learned certain goal configurations, the agent can learn an option to achieve the goal configuration and a distance function that predicts at least one of a distance and a duration to the goal configuration under the learned option. This distance function prediction may be incorporated as a state feature of the agent.

Method and system for continual learning in an intelligent artificial agent

A system that monitors and assesses the moods of subjects with neurological disorders, like bipolar disorder, by analyzing normal conversational speech to identify speech data that is then analyzed through an automated speech data classifier. The classifier may be based on a vector, separator, hyperplane, decision boundary, or other set of rules to classify one or more mood states of a subject. The system classifier is used to assess current mood state, predicted instability, and/or a change in future mood state, in particular for subjects with bipolar disorder.

Mood monitoring of bipolar disorder using speech analysis

Growing community of inventors

Ann Arbor, MI, United States of America

Satinder Singh Baveja