Dynamics based control with PSRs
نویسندگان
چکیده
We present an extension of the Dynamics Based Control (DBC) paradigm to environment models based on Predictive State Representations (PSRs). We show an approximate greedy version of the DBC for PSR model, EMT-PSR, and demonstrate how this algorithm can be applied to solve several control problems. We then provide some classifications and requirements of PSR environment models that are necessary for the EMT-PSR algorithm to operate.
منابع مشابه
Predictive State Representations: A New Theory for Modeling Dynamical Systems
Modeling dynamical systems, both for control purposes and to make predictions about their behavior, is ubiquitous in science and engineering. Predictive state representations (PSRs) are a recently introduced class of models for discrete-time dynamical systems. The key idea behind PSRs and the closely related OOMs (Jaeger’s observable operator models) is to represent the state of the system as a...
متن کاملApproximate predictive state representations
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses on trying to learn exact models, an approach that cannot scale to complex dynamical systems. In contrast, our work takes the first steps in developing a theory of approximate PSRs. We examine the consequences of using ...
متن کاملOnline Discovery and Learning of Predictive State Representations
Predictive state representations (PSRs) are a method of modeling dynamical systems using only observable data, such as actions and observations, to describe their model. PSRs use predictions about the outcome of future tests to summarize the system state. The best existing techniques for discovery and learning of PSRs use a Monte Carlo approach to explicitly estimate these outcome probabilities...
متن کاملEfficient learning and planning with compressed predictive states
Predictive state representations (PSRs) offer an expressive framework for modelling partially observable systems. By compactly representing systems as functions of observable quantities, the PSR learning approach avoids using local-minima prone expectationmaximization and instead employs a globally optimal moment-based algorithm. Moreover, since PSRs do not require a predetermined latent state ...
متن کاملCompressed Predictive States Efficient Learning and Planning with Compressed Predictive States
Predictive state representations (PSRs) offer an expressive framework for modelling partially observable systems. By compactly representing systems as functions of observable quantities, the PSR learning approach avoids using local-minima prone expectationmaximization and instead employs a globally optimal moment-based algorithm. Moreover, since PSRs do not require a predetermined latent state ...
متن کامل