Computer Science – Learning
Scientific paper
2009-03-17
POSTER 2009
Computer Science
Learning
accepted, noted that the initial path was 217 steps long
Scientific paper
Many reinforcement learning exploration techniques are overly optimistic and
try to explore every state. Such exploration is impossible in environments with
the unlimited number of states. I propose to use simulated exploration with an
optimistic model to discover promising paths for real exploration. This reduces
the needs for the real exploration.
No associations
LandOfFree
Optimistic Simulated Exploration as an Incentive for Real Exploration 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 Optimistic Simulated Exploration as an Incentive for Real Exploration, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimistic Simulated Exploration as an Incentive for Real Exploration will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-491471