Dynamics based control with PSRs

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. Categories and Subject Descriptors I.2.8 [Artificial Intelligence]: Problem Solving, Control Methods, and Search--Control theory; I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence--Multiagent systems General Terms Algorithms, Performance, Experimentation Keywords Dynamics Based Control, Predictive State Representation

• Type: Conference
• Year: 2008
• Where: ATAL
• Authors: Ariel Adam, Zinovi Rabinovich, Jeffrey S. Rosenschein
• Keywords: ATAL 2008, Dynamics Based Control, Environment Models, Intelligent Agents, Predictive State Representation