Results 81 to 90 of about 1,056,132 (188)

Learn to Steer through Deep Reinforcement Learning [PDF]

Sensors, 2018
It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-
Keyu Wu 0002, Mahdi Abolfazli Esfahani, Shenghai Yuan 0001, Han Wang 0001   +3 more
openaire   +5 more sources

Quality of service optimization algorithm based on deep reinforcement learning in software defined network

物联网学报, 2023
Deep reinforcement learning has strong abilities of decision-making and generalization and often applies to the quality of service (QoS) optimization in software defined network (SDN).However, traditional deep reinforcement learning algorithms have ...
Cenhuishan LIAO, Junyan CHEN, Guanping LIANG, Xiaolan XIE, Xiaoye LU   +4 more
doaj   +2 more sources

Deep Reinforcement Learning Approach for Traffic Light Control and Transit Priority

Future Transportation
This study investigates the use of deep reinforcement learning techniques to improve traffic signal control systems through the integration of deep learning and reinforcement learning approaches.
Saeed Mansouryar, Chiara Colombaroni, Natalia Isaenko, Gaetano Fusco   +3 more
doaj   +1 more source

Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations

IEEE Access, 2020
The motivation behind our work is to review and analyze the most relevant studies on deep reinforcement learning-based object manipulation. Various studies are examined through a survey of existing literature and investigation of various aspects, namely,
Marwan Qaid Mohammed, Kwek Lee Chung, Chua Shing Chyi   +2 more
doaj   +1 more source

Deep Successor Reinforcement Learning

CoRR, 2016
Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map.
Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam, Samuel J. Gershman   +3 more
openaire   +2 more sources

Quantum Deep Recurrent Reinforcement Learning

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Recent advances in quantum computing (QC) and machine learning (ML) have drawn significant attention to the development of quantum machine learning (QML). Reinforcement learning (RL) is one of the ML paradigms which can be used to solve complex sequential decision making problems.
openaire   +2 more sources

Learning Mobile Manipulation through Deep Reinforcement Learning

Sensors, 2020
Mobile manipulation has a broad range of applications in robotics. However, it is usually more challenging than fixed-base manipulation due to the complex coordination of a mobile base and a manipulator.
Cong Wang, Qifeng Zhang, Qiyan Tian, Shuo Li, Xiaohui Wang, David Lane, Yvan Petillot, Sen Wang   +7 more
doaj   +1 more source

Dynamic optimization of stand structure in Pinus yunnanensis secondary forests based on deep reinforcement learning and structural prediction

Frontiers in Plant Science
IntroductionThe rational structure of forest stands plays a crucial role in maintaining ecosystem functions, enhancing community stability, and ensuring sustainable management.
Jian Zhao, Jianming Wang, Jiting Yin, Yuling Chen, Baoguo Wu   +4 more
doaj   +1 more source

Learning to Walk Via Deep Reinforcement Learning

Robotics: Science and Systems XV, 2019
RSS 2019, https://sites.google.com/view/minitaur-locomotion/
Tuomas Haarnoja, Aurick Zhou, Sehoon Ha, Jie Tan 0001, George Tucker, Sergey Levine   +5 more
openaire   +2 more sources

Z-Score Experience Replay in Off-Policy Deep Reinforcement Learning

Sensors
Reinforcement learning, as a machine learning method that does not require pre-training data, seeks the optimal policy through the continuous interaction between an agent and its environment.
Yana Yang, Meng Xi, Huiao Dai, Jiabao Wen, Jiachen Yang   +4 more
doaj   +1 more source