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
-
Discovering and Exploiting Skills in Hierarchical Reinforcement Learning
by: Zhigang Huang
Published: (2024-01-01) -
Reward monitoring in the frontopolar cortex of macaques
by: Lorenzo Ferrucci, et al.
Published: (2025-05-01) -
Exploring the effects of risk-taking, exploitation, and exploration on divergent thinking under group dynamics
by: Tsutomu HARADA
Published: (2022-09-01) -
A Detailed Comparison of Two New Heuristic Algorithms Based on Gazelles Behavior
by: Emine Baş
Published: (2024-06-01) -
Exploration Techniques in Reinforcement Learning for Autonomous Vehicles
by: Ammar Khaleel, et al.
Published: (2024-11-01)