Results 1 to 10 of about 13,589 (169)

Entropy Regularization in Deep Reinforcement Learning: A Structured Review Across Classical Control, Generative Policies, and Reasoning Language Models [PDF]

Entropy
Entropy regularization is a recurring mechanism in reinforcement learning (RL), but its meaning changes across algorithmic settings. In classical online RL, entropy encourages exploration and smooths policy improvement; in inverse RL and imitation ...
Giorgio Taricco
doaj   +2 more sources

Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones [PDF]

IEEE Robotics and Automation Letters, 2021
RA-L and ICRA 2021.
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair 0003, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg   +9 more
openaire   +4 more sources

Reinforcement Learning: Theory and Applications in HEMS

Energies, 2022
The steep rise in reinforcement learning (RL) in various applications in energy as well as the penetration of home automation in recent years are the motivation for this article.
Omar Al-Ani, Sanjoy Das
doaj   +1 more source

Evo-RL

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2021
9 pages, 7 ...
Hallawa, Ahmed, Born, Thorsten, Schmeink, Anke, Dartmann, Guido, Peine, Arne, Martin, Lukas, Iacca, Giovanni, Eiben, A. E., Ascheid, Gerd   +8 more
openaire   +3 more sources

Review of Path Planning Techniques Based on Reinforcement Learning [PDF]

Jisuanji gongcheng, 2021
Path planning is one of the key technologies for autonomous navigation of mobile robots.It aims at planning a collision free optimal path from the current position to the destination in real time.This paper introduces the path planning techniques that ...
YAN Jiaojie, ZHANG Qieshi, HU Xiping
doaj   +1 more source

Distributed Reinforcement Learning with ADMM-RL [PDF]

2019 American Control Conference (ACC), 2019
This paper presents a new algorithm for distributed Reinforcement Learning (RL). RL is an artificial intelligence (AI) control strategy such that controls for highly nonlinear systems over multi-step time horizons may be learned by experience, rather than directly computed on the fly by optimization.
Peter A. Graf, Jennifer Annoni, Christopher J. Bay, David Biagioni, Devon Sigler, Monte Lunacek, Wesley B. Jones   +6 more
openaire   +1 more source

Entropy regularized reinforcement learning using large deviation theory

Physical Review Research, 2023
Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics.
Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin, Rahul V. Kulkarni   +3 more
doaj   +1 more source

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

Applied Sciences, 2023
The use of reinforcement learning (RL) for dynamic obstacle avoidance (DOA) algorithms and path planning (PP) has become increasingly popular in recent years. Despite the importance of RL in this growing technological era, few studies have systematically
Khawla Almazrouei, Ibrahim Kamel, Tamer Rabie   +2 more
doaj   +1 more source

ADAPTIVE SELECTION OF AUXILIARY OBJECTIVES IN MULTIOBJECTIVE EVOLUTIONARY ALGORITHMS [PDF]

Научно-технический вестник информационных технологий, механики и оптики, 2016
Subject of Research.We propose to modify the EA+RL method, which increases efficiency of evolutionary algorithms by means of auxiliary objectives.
I. A. Petrova, A. S. Buzdalova, A. A. Shalyto   +2 more
doaj   +1 more source

Performance Analysis of Reinforcement Learning Techniques for Augmented Experience Training Using Generative Adversarial Networks

Applied Sciences, 2022
This paper aims at analyzing the performance of reinforcement learning (RL) agents when trained in environments created by a generative adversarial network (GAN).
Smita Mahajan, Shruti Patil, Moinuddin Bhavnagri, Rashmi Singh, Kshitiz Kalra, Bhumika Saini, Ketan Kotecha, Jatinderkumar Saini   +7 more
doaj   +1 more source