Learning for Adaptive Real-time Search

Details Learning for Adaptive Real-time Search Learning for Adaptive Real-time Search

2004-07-06

arxiv.org/abs/cs/0407016v1

Computer Science

Artificial Intelligence

Scientific paper

Real-time heuristic search is a popular model of acting and learning in intelligent autonomous agents. Learning real-time search agents improve their performance over time by acquiring and refining a value function guiding the application of their actions. As computing the perfect value function is typically intractable, a heuristic approximation is acquired instead. Most studies of learning in real-time search (and reinforcement learning) assume that a simple value-function-greedy policy is used to select actions. This is in contrast to practice, where high-performance is usually attained by interleaving planning and acting via a lookahead search of a non-trivial depth. In this paper, we take a step toward bridging this gap and propose a novel algorithm that (i) learns a heuristic function to be used specifically with a lookahead-based policy, (ii) selects the lookahead depth adaptively in each state, (iii) gives the user control over the trade-off between exploration and exploitation. We extensively evaluate the algorithm in the sliding tile puzzle testbed comparing it to the classical LRTA* and the more recent weighted LRTA*, bounded LRTA*, and FALCONS. Improvements of 5 to 30 folds in convergence speed are observed.

Affiliated with

Also associated with

No associations

Rating

Learning for Adaptive Real-time Search 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 for Adaptive Real-time Search, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning for Adaptive Real-time Search will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-729224