Results 71 to 80 of about 1,629,210 (315)

Cross Learning in Deep Q-Networks

, 2020
In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors.
Wang, Xing, Vinel, Alexander
openaire   +2 more sources

Modeling hepatic fibrosis in TP53 knockout iPSC‐derived human liver organoids

Molecular Oncology, EarlyView.
This study developed iPSC‐derived human liver organoids with TP53 gene knockout to model human liver fibrosis. These organoids showed elevated myofibroblast activation, early disease markers, and advanced fibrotic hallmarks. The use of profibrotic differentiation medium further amplified the fibrotic signature seen in the organoids.
Mustafa Karabicici, Soheil Akbari, Ceyda Caliskan, Canan Celiker, Ozden Oz, Leman Binokay, Gökhan Karakulah, Serif Senturk, Esra Erdal   +8 more
wiley   +1 more source

Two-Stage Optimization Model Based on Neo4j-Dueling Deep Q Network

Energies
To alleviate the power flow congestion in active distribution networks (ADNs), this paper proposes a two-stage load transfer optimization model based on Neo4j-Dueling DQN.
Tie Chen, Pingping Yang, Hongxin Li, Jiaqi Gao, Yimin Yuan   +4 more
doaj   +1 more source

A fast learning approach for autonomous navigation using a deep reinforcement learning method

Electronics Letters, 2021
Deep reinforcement learning‐based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a ...
Muhammad Mudassir Ejaz, Tong Boon Tang, Cheng‐Kai Lu   +2 more
doaj   +1 more source

Causal Deep Q Networks

Deep Q Networks (DQN) have shown remarkable success in various reinforcement learning tasks. However, their reliance on associative learning often leads to the acquisition of spurious correlations, hindering their problem-solving capabilities. In this paper, we introduce a novel approach to integrate causal principles into DQNs, leveraging the PEACE ...
Khelifi, Elouanes, Saki, Amir, Faghihi, Usef   +2 more
openaire   +2 more sources

Dynamic Frame skip Deep Q Network

, 2016
Deep Reinforcement Learning methods have achieved state of the art performance in learning control policies for the games in the Atari 2600 domain. One of the important parameters in the Arcade Learning Environment (ALE) is the frame skip rate. It decides the granularity at which agents can control game play.
Srinivas, Aravind, Sharma, Sahil, Ravindran, Balaraman   +2 more
openaire   +2 more sources

PYCR1 inhibition in bone marrow stromal cells enhances bortezomib sensitivity in multiple myeloma cells by altering their metabolism

Molecular Oncology, EarlyView.
This study investigated how PYCR1 inhibition in bone marrow stromal cells (BMSCs) indirectly affects multiple myeloma (MM) cell metabolism and viability. Culturing MM cells in conditioned medium from PYCR1‐silenced BMSCs impaired oxidative phosphorylation and increased sensitivity to bortezomib.
Inge Oudaert, Lauren van den Broecke, Osman Aksoy, Judith Lind, Sonia Vallet, Arne Van der Vreken, Gamze Ates, Ann Massie, Ken Maes, Kim De Veirman, Elke De Bruyne, Karin Vanderkerken, Klaus Podar, Eline Menu   +13 more
wiley   +1 more source

Multi-Agent DRL Approach for Energy-Efficient Resource Allocation in URLLC-Enabled Grant-Free NOMA Systems

IEEE Open Journal of the Communications Society, 2023
Grant-free non-orthogonal multiple access (GF-NOMA) has emerged as a promising access technology for the fifth generation and beyond wireless networks that enable ultra-reliable and low-latency communications (URLLC) to ensure low access latency and high
Duc-Dung Tran, Shree Krishna Sharma, Vu Nguyen Ha, Symeon Chatzinotas, Isaac Woungang   +4 more
doaj   +1 more source

On The Transferability of Deep-Q Networks

, 2021
Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets. While exploiting TL is a well established and successful training practice in Supervised Learning (SL), its ...
Sabatelli, Matthia, Geurts, Pierre
openaire   +3 more sources

Multifunctional Radar Cognitive Jamming Decision Based on Dueling Double Deep Q-Network

IEEE Access, 2022
To solve the inefficient and imprecise problem using the Deep Q-network (DQN) algorithm for the radar jamming decision, this paper proposes a multifunctional radar jamming decision optimization method based on the Dueling Double Deep Q-network (D3QN ...
Lu Feng, Songsheng Liu, Huazhi Xu
semanticscholar   +1 more source