Improving state-action space exploration in reinforcement learning using geometric properties
Details
Melbourne, USA. Date of Talk: 2017-12-12
Speakers
Event
Improving state-action space exploration in reinforcement learning using geometric properties
Learning a model or learning a policy that optimizes some objective function relies on data-sets that describe the behavior of the system. When such sets are unavailable or insufficient, additional data may be generated through new experiments (if feasible) or through simulations (if an accurate model is available). In this paper we describe a third alternative that is based on the availability of a qualitative model of the physical system. In particular, we show how the number of experiments used in reinforcement learning can be reduced by leveraging geometric properties of the system. The geometric properties are independent of any particular instantiation of the qualitative model. As an illustrative example, we apply our approach to a cart-pole system.
Additional information
Focus Areas
Our work is centered around a series of Focus Areas that we believe are the future of science and technology.
Licensing & Commercialization Opportunities
We’re continually developing new technologies, many of which are available for Commercialization.
News
Our scientists and staffers are active members and contributors to the science and technology communities.