Timezone: »

Multi-Step Dyna Planning for Policy Evaluation and Control
Hengshuai Yao · Richard Sutton · Shalabh Bhatnagar · Dongcui Diao · Csaba Szepesvari

Wed Dec 09 07:00 PM -- 11:59 PM (PST) @
We extend Dyna planning architecture for policy evaluation and control in two significant aspects. First, we introduce a multi-step Dyna planning that projects the simulated state/feature many steps into the future. Our multi-step Dyna is based on a multi-step model, which we call the {\em $\lambda$-model}. The $\lambda$-model interpolates between the one-step model and an infinite-step model, and can be learned efficiently online. Second, we use for Dyna control a dynamic multi-step model that is able to predict the results of a sequence of greedy actions and track the optimal policy in the long run. Experimental results show that Dyna using the multi-step model evaluates a policy faster than using single-step models; Dyna control algorithms using the dynamic tracking model are much faster than model-free algorithms; further, multi-step Dyna control algorithms enable the policy and value function to converge much faster to their optima than single-step Dyna algorithms.

Author Information

Hengshuai Yao (University of Alberta)
Richard Sutton (DeepMind, U Alberta)

Richard S. Sutton is a professor and iCORE chair in the department of computing science at the University of Alberta. He is a fellow of the Association for the Advancement of Artificial Intelligence and co-author of the textbook "Reinforcement Learning: An Introduction" from MIT Press. Before joining the University of Alberta in 2003, he worked in industry at AT&T and GTE Labs, and in academia at the University of Massachusetts. He received a PhD in computer science from the University of Massachusetts in 1984 and a BA in psychology from Stanford University in 1978. Rich's research interests center on the learning problems facing a decision-maker interacting with its environment, which he sees as central to artificial intelligence. He is also interested in animal learning psychology, in connectionist networks, and generally in systems that continually improve their representations and models of the world.

Shalabh Bhatnagar (Indian Institute of Science)
Dongcui Diao
Csaba Szepesvari (University of Alberta)

More from the Same Authors