Results 11 to 20 of about 1,436,683 (204)

Z-Score Experience Replay in Off-Policy Deep Reinforcement Learning [PDF]

open access: yesSensors
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   +4 more
doaj   +2 more sources

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning [PDF]

open access: greenIEEE International Conference on Robotics and Automation, 2018
Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, but typically require a very large number of samples to achieve good performance.
Anusha Nagabandi   +3 more
openalex   +3 more sources

Learning agile soccer skills for a bipedal robot with deep reinforcement learning [PDF]

open access: yesScience Robotics, 2023
We investigated whether deep reinforcement learning (deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies.
Tuomas Haarnoja   +27 more
semanticscholar   +1 more source

The Dormant Neuron Phenomenon in Deep Reinforcement Learning [PDF]

open access: yesInternational Conference on Machine Learning, 2023
In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing number of inactive neurons, thereby affecting network expressivity.
Ghada Sokar   +3 more
semanticscholar   +1 more source

Deep Reinforcement Learning for Autonomous Driving: A Survey [PDF]

open access: yesIEEE transactions on intelligent transportation systems (Print), 2020
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments.
B. R. Kiran   +6 more
semanticscholar   +1 more source

Loss of Plasticity in Continual Deep Reinforcement Learning [PDF]

open access: yesCoLLAs, 2023
The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL) approaches under varying degrees of non-stationarity.
Zaheer Abbas   +4 more
semanticscholar   +1 more source

On the Use of Deep Reinforcement Learning for Visual Tracking: A Survey

open access: yesIEEE Access, 2021
This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning.
Giorgio Cruciata   +2 more
doaj   +1 more source

Deep Reinforcement Learning with Plasticity Injection [PDF]

open access: yesNeural Information Processing Systems, 2023
A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered by the complex ...
Evgenii Nikishin   +6 more
semanticscholar   +1 more source

Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning

open access: yesIEEE Access, 2023
While significant research advances have been made in the field of deep reinforcement learning, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to ...
Maziar Gomrokchi   +4 more
doaj   +1 more source

An Overview of Machine Learning, Deep Learning, and Reinforcement Learning-Based Techniques in Quantitative Finance: Recent Progress and Challenges

open access: yesApplied Sciences, 2023
Forecasting the behavior of the stock market is a classic but difficult topic, one that has attracted the interest of both economists and computer scientists.
Santosh Kumar Sahu   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy