Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning

Details Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning

2009-04-03

arxiv.org/abs/0904.0546v1

Computer Science

Artificial Intelligence

7 pages

Scientific paper

A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provides for Time Hopping similar abilities to what eligibility traces provide for conventional Reinforcement Learning. It propagates values from one state to all of its temporal predecessors using a state transitions graph. Experiments on a simulated biped crawling robot confirm that Eligibility Propagation accelerates the learning process more than 3 times.

Affiliated with

Also associated with

No associations

Rating

Eligibility Propagation to Speed up Time Hopping for 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 Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-150653