Decision Making Agent Searching for Markov Models in Near-Deterministic World

Details Decision Making Agent Searching for Markov Models in Near-Deterministic World Decision Making Agent Searching for Markov Models in Near-Deterministic World

2011-02-27

arxiv.org/abs/1102.5561v2

Computer Science

Artificial Intelligence

Draft

Scientific paper

Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illustrate the properties of architecture in the near deterministic Ms. Pac-Man game. We analyze the architecture from the point of view of evolutionary, individual, and social learning.

Affiliated with

Also associated with

No associations

Rating

Decision Making Agent Searching for Markov Models in Near-Deterministic World 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 Decision Making Agent Searching for Markov Models in Near-Deterministic World, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Decision Making Agent Searching for Markov Models in Near-Deterministic World will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-424282