🚀 go-pugleaf

University of Colorado at Boulder
Department of Computer Science
ECOT 717 Engineering Center
Campus Box 430
Boulder, Colorado 803090430
(303) 4927514, FAX: (303) 4922844

CS COLLOQUIUM
Fast Reinforcement Learning in Large Continuous Domains
Greg Grudic
University of Pennsylvania
April 26, 2001
3:30  4:30 PM
Engineering Center Classroom 245

Refreshments will be served afterwards in ECOT 831

Reinforcement Learning (RL) is a framework by which an agent autonomously 
learns to improve the rewards it receives from its environment, thus 
conceptually embodying one of the fundamental aims of AI. RL algorithms 
have been shown to be effective on a variety of discrete problem domains, 
where simulation allows millions of learning episodes to be executed. 
However, the application of RL to large continuous problem domains where 
only limited numbers of learning episodes can be afforded, has not met with 
as much success. I propose a set of methods in which the policy definitions 
used to encode how an agent interacts with its environment are represented 
by a finite set of parameters. Policy Gradient (PG) RL is used to 
incrementally modify this parameterized policy along a gradient of improved 
reward. I will describe three new PG algorithms we have developed to make 
RL feasible in high dimensional continuous state spaces: Boundary Localized 
Reinforcement Learning (BLRL), Action Transition Policy Gradient (ATPG), 
and Deterministic Policy Gradient (DPG). These algorithms directly encode 
prior domain knowledge, vastly improving convergence speed, and are all 
theoretically guaranteed to converge to locally optimal control policies. 
The computational feasibility of these algorithms is demonstrated 
experimentally on simulated and real problems taken from robotics. We show 
convergence to locally optimal policies in less than a few hundred 
episodes, unlike other PG algorithms that require orders of magnitude more 
episodes to converge.

Host:  Mike Mozer
------------------------------
http://www.cs.colorado.edu/department/events/colloquia/colloquia.html

Sign Language Interpreters Available Upon Request.  Please contact Jane 
Obrecht, Department of
Computer Science, Engineering  ECOT 722, 303-492-6101, at least five days 
prior to the colloquium.

_______________________________________________
cscolloq mailing list
cscolloq@cs.colorado.edu
http://www.cs.colorado.edu/mailman/listinfo/cscolloq