Other

Sony Group Corporation

Sony Corporation of America

Mark Ring

James MacGlashan

Satinder Singh Baveja

Kaushik Subramanian

Roberto Capobianco

Varun Kompella

Peter R Wurman

Tom Schaul

Peter Stone

Samuel Barrett

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

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

An automated child safety unlocking system which disengages the child safety locks and may unlock the vehicle door in appropriate circumstances such as when the vehicle ignition has been turned to the off position or when engine is stopped. The automated child safety unlocking system enables operability of the interior vehicle doors by an occupant to allow unencumbered egress from the vehicle to prevent a child or other individual from being trapped in the vehicle. The result is reduced risk that children or other vehicle occupants become dangerously entrapped within an overly hot, cold, or dangerous vehicle.

Automatic child safety lock release

Building a forecast for an autonomous agent at least comprises assigning a selected parameter of the autonomous agent to a scalar variable, adding a new policy to a set of policies where the new policy maps internal states of the autonomous agent to actions of the autonomous agent in which the mapping may optimize the scalar variable, and adding a new forecast to a set of forecasts where the forecast at least comprises a prediction regarding future values of the scalar variable following execution of the new policy, regardless whether the agent ever actually chooses to take actions in accordance with said new policy. A state of the autonomous agent may be evaluated following completion of each of the agent's actions by comparing the agent's state information with the predicted values of one or more forecasts. Whether to build an additional forecast may be determined based on the evaluation.

Method for creating predictive knowledge structures from experience in an artificial agent

A method and system comprise providing means and method for producing, modifying, and/or exploiting the structure of a policy manifold. Each of the policies at least comprises information for mapping state and/or sensory information as input to action preferences as output. One or more processing units assign each of the policies a policy coordinate on a policy manifold. The policy coordinate may in part be determined by a dissimilarity matrix or other means for organizing the coordinates of the policies on the policy manifold according to the properties of the policies and the topology of the policy manifold. The policy manifold comprises a dimensionality that is lower than a combined dimensionality of the input and the output, wherein the policy manifold at least in part determines a behavior of the intelligent artificial agent.

Method and system for mapping states and actions of an intelligent agent

A portable, adjustable seat for suspension between the gunwales of a canoe, when used in a first orientation as a canoe seat, of a rigid construction that permits its use in a second, reverse orientation as a camp stool, when camping. The seat comprises a pair of cross members spaced from one another by a pair of braces to form a generally rectangular platform, a fabric sheet extending from one cross member to the other within the rectangular platform to provide a seating area, and left and right pairs of legs shaped to attach to the left and right ends of the pair of cross members (in the gunwales of the canoe) to suspend the seating area below and within the gunwales in the first orientation and to act as stool legs in the second orientation, the entire construction being sufficiently rigid to support the weight of a person when used in either orientation. Preferably the fitting of the legs with the right and left ends of the pair of cross members may be independently adjusted and locked to accommodate differing canoe gunwale widths or the change in width along the length of a given canoe, while maintaining rigidity and support.

Growing community of inventors

Anaheim, CA, United States of America

Mark Ring