Learning Policies with External Memory

Details Learning Policies with External Memory Learning Policies with External Memory

2001-03-02

arxiv.org/abs/cs/0103003v1

In Bratko, I., and Dzeroski, S., eds., Machine Learning: Proceedings of the Sixteenth International Conference, pp. 307-314. M

Computer Science

Learning

8 pages

Scientific paper

In order for an agent to perform well in partially observable domains, it is usually necessary for actions to depend on the history of observations. In this paper, we explore a {\it stigmergic} approach, in which the agent's actions include the ability to set and clear bits in an external memory, and the external memory is included as part of the input to the agent. In this case, we need to learn a reactive policy in a highly non-Markovian domain. We explore two algorithms: SARSA(\lambda), which has had empirical success in partially observable domains, and VAPS, a new algorithm due to Baird and Moore, with convergence guarantees in partially observable domains. We compare the performance of these two algorithms on benchmark problems.

Affiliated with

Also associated with

No associations

Rating

Learning Policies with External Memory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning Policies with External Memory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Policies with External Memory will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-301353