Searching for Plannable Domains can Speed up Reinforcement Learning

Details Searching for Plannable Domains can Speed up Reinforcement Learning Searching for Plannable Domains can Speed up Reinforcement Learning

2002-12-10

arxiv.org/abs/cs/0212025v1

Computer Science

Artificial Intelligence

Scientific paper

Reinforcement learning (RL) involves sequential decision making in uncertain environments. The aim of the decision-making agent is to maximize the benefit of acting in its environment over an extended period of time. Finding an optimal policy in RL may be very slow. To speed up learning, one often used solution is the integration of planning, for example, Sutton's Dyna algorithm, or various other methods using macro-actions. Here we suggest to separate plannable, i.e., close to deterministic parts of the world, and focus planning efforts in this domain. A novel reinforcement learning method called plannable RL (pRL) is proposed here. pRL builds a simple model, which is used to search for macro actions. The simplicity of the model makes planning computationally inexpensive. It is shown that pRL finds an optimal policy, and that plannable macro actions found by pRL are near-optimal. In turn, it is unnecessary to try large numbers of macro actions, which enables fast learning. The utility of pRL is demonstrated by computer simulations.

Affiliated with

Also associated with

No associations

Rating

Searching for Plannable Domains can Speed up Reinforcement Learning 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 Searching for Plannable Domains can Speed up Reinforcement Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Searching for Plannable Domains can Speed up Reinforcement Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-637961