Re-exploration of ε-greedy in deep reinforcement learning
This paper presents re-exploration as a method for improving the existing method for balancing the exploration/exploitation problem integral to reinforcement learning. The proposed method uses a ε-greedy method called “decreasing epsilon,” which reiterate the method after a certain period of episode...
Saved in:
Main Authors: | Muhamad Amin, Muhamad Ridzuan Radin, Othman, Mohd. Fauzi |
---|---|
Format: | Conference or Workshop Item |
Published: |
2021
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/96174/ http://dx.doi.org/10.1007/978-981-16-4803-8_27 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Influence of natural fibers on the mechanical properties and biodegradation of poly(lactic acid) and poly(ε‐caprolactone) composites: a review
by: Wahit, Mat Uzir, et al.
Published: (2012) -
Effects of square openings in reinforced concrete deep beams
by: Noor Rahaman, Yahya
Published: (2014) -
Ultimate capacity and reinforcement area requirement for bridge girder using various FRP re-bars
by: Fayyadh, M.M., et al.
Published: (2010) -
Bearing capacity charts of soft soil reinforced by deep mixing
by: Rashid, A. S. A., et al.
Published: (2017) -
Behaviour of Reinforced Concrete Deep Beams with Openings in the Shear Zone
by: Chin, Siew Choo, et al.
Published: (2015)