M-Learning: Heuristic Approach for Delayed Rewards in Reinforcement Learning
The current design of reinforcement learning methods requires extensive computational resources. Algorithms such as Deep Q-Network (DQN) have obtained outstanding results in advancing the field. However, the need to tune thousands of parameters and run millions of training episodes remains a signifi...
Saved in:
Main Authors: | Cesar Andrey Perdomo Charry, Marlon Sneider Mora Cortes, Oscar J. Perdomo |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-06-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/13/13/2108 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Adaptive sequential sampling for reliability estimation of binary functions
by: Miroslav Vořechovský
Published: (2022-08-01) -
Complexification through gradual involvement and reward Providing in deep reinforcement learning
by: E. V. Rulko,
Published: (2024-12-01) -
Strategic Decision-Making in SMEs: A Review of Heuristics and Machine Learning for Multi-Objective Optimization
by: Gines Molina-Abril, et al.
Published: (2025-07-01) -
Optimizing travel time reliability with XAI: A Virginia interstate network case using machine learning and meta-heuristics
by: Navid Khorshidi, et al.
Published: (2025-09-01) -
SBOA: A Novel Heuristic Optimization Algorithm
by: Qi Diao, et al.
Published: (2024-02-01)