Transition Based Discount Factor for Model Free Algorithms in Reinforcement Learning
Reinforcement Learning (RL) enables an agent to learn control policies for achieving its long-term goals. One key parameter of RL algorithms is a discount factor that scales down future cost in the state’s current value estimate. This study introduces and analyses a transition-based discount factor...
Main Authors: | Abhinav Sharma, Ruchir Gupta, K. Lakshmanan, Atul Gupta |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/7/1197 |
Similar Items
-
An Efficient Hardware Implementation of Reinforcement Learning: The Q-Learning Algorithm
by: Sergio Spano, et al.
Published: (2019-01-01) -
Machine Learning for Traffic Control of Unmanned Mining Machines : Using the Q-learning and SARSA algorithms
by: Gustafsson, Robin, et al.
Published: (2019) -
Reinforcement Learning Based Stochastic Shortest Path Finding in Wireless Sensor Networks
by: Wenwen Xia, et al.
Published: (2019-01-01) -
Using combination of actions in reinforcement learning
by: Marcelo J. Karanik, et al.
Published: (2010-04-01) -
MARLA-SG: Multi-Agent Reinforcement Learning Algorithm for Efficient Demand Response in Smart Grid
by: Sally Aladdin, et al.
Published: (2020-01-01)