Title :
Time varying nonlinear Policy Gradients
Author :
Theodorou, Evangelos A. ; Dvijotham, Krishnamurthy ; Todorov, Emo
Author_Institution :
Sch. of Aerosp. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
We derive Policy Gradients(PGs) with time varying parameterizations for nonlinear diffusion processes affine in noise. The resulting policies have the form of reward weighted gradient. The analysis is in continuous time and includes the case of linear and nonlinear parameterizations. Examples on stochastic control problems for diffusions processes are provided.
Keywords :
continuous time systems; control system analysis; linear systems; nonlinear control systems; stochastic systems; PG; continuous time analysis; linear parameterization; nonlinear diffusion process; nonlinear parameterization; reward weighted gradient; stochastic control problems; time varying nonlinear policy gradients; time varying parameterizations; Aerodynamics; Diffusion processes; Educational institutions; Equations; Linear programming; Noise; Trajectory;
Conference_Titel :
Decision and Control (CDC), 2013 IEEE 52nd Annual Conference on
Conference_Location :
Firenze
Print_ISBN :
978-1-4673-5714-2
DOI :
10.1109/CDC.2013.6761122