Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence

Details Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence

2006-03-28

arxiv.org/abs/cs/0603110v1

Proc. 17th International Conf. on Algorithmic Learning Theory (ALT 2006) pages 334-347

Computer Science

Learning

15 pages

Scientific paper

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions.

Affiliated with

Also associated with

No associations

Rating

Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence 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 Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-463393