34,804 Hits in 5.8 sec

How to Make Deep RL Work in Practice [article]

Nirnai Rao, Elie Aljalbout, Axel Sauer, Sami Haddadin
2020 arXiv   pre-print
In recent years, challenging control problems became solvable with deep reinforcement learning (RL).  ...  We make suggestions which of those techniques to use by default and highlight areas that could benefit from a solution specifically tailored to RL.  ...  ACKNOWLEDGEMENTS We greatly acknowledge the funding of this work by Microsoft Germany and the Alfried Krupp von Bohlen und Halbach Foundation.  ... 
arXiv:2010.13083v2 fatcat:tbjrr44gfzfybbgyqsdwzstoya

ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives [article]

Toshinori Kitamura, Ryo Yonetani
2021 arXiv   pre-print
As a case study, we show that how combining these two features of ShinRL makes it easier to analyze the behavior of deep Q learning.  ...  Existing RL libraries typically allow users to evaluate practical performances of deep RL algorithms through returns.  ...  Acknowledgments The authors would like to thank Masashi Hamaya for helpful feedback on the manuscript.  ... 
arXiv:2112.04123v1 fatcat:iqcj5ufo4rfx3pzoua4nytjd3e

Deep Reinforcement Learning and its Neuroscientific Implications [article]

Matthew Botvinick, Jane X. Wang, Will Dabney, Kevin J. Miller, Zeb Kurth-Nelson
2020 arXiv   pre-print
Deep RL offers a comprehensive framework for studying the interplay among learning, representation and decision-making, offering to the brain sciences a new set of research tools and a wide range of novel  ...  In the present review, we provide a high-level introduction to deep RL, discuss some of its initial applications to neuroscience, and survey its wider implications for research on brain and behavior, concluding  ...  We have focused on how deep RL can help neuroscience, but as should be clear from much of what we have written, deep RL is a work in progress.  ... 
arXiv:2007.03750v1 fatcat:nl6ggmxli5fjlnub6y2w6nnvpe

The Implementation of Deep Reinforcement Learning in E-Learning and Distance Learning: Remote Practical Work

Abdelali El Gourari, Mustapha Raoufi, Mohammed Skouri, Fahd Ouatik, Salvatore Carta
2021 Mobile Information Systems  
The objective of this work is to propose a recommendation system based on deep quality-learning networks (DQNs) to recommend and direct students in advance of doing the RPW according to their skills of  ...  At the Faculty of Sciences Semlalia, Cadi Ayyad University Marrakech, Morocco, we have created a simple electronic platform for remote practical work (RPW), and its results have been good in terms of student  ...  Deep RL versus Deep Learning. We understood how neural networks can help the agent learn the perfect actions.  ... 
doi:10.1155/2021/9959954 fatcat:3x4kk7mrzjbq3o5m6ueor2o72q

Reinforcement Learning in Practice: Opportunities and Challenges [article]

Yuxi Li
2022 arXiv   pre-print
We conclude with a discussion, attempting to answer: "Why has RL not been widely adopted in practice yet?" and "When is RL helpful?".  ...  In this article, we first give a brief introduction to reinforcement learning (RL), and its relationship with deep learning, machine learning and AI.  ...  The question about RL algorithm selection may be from a student wanting to try a toy example/benchmark, or from a company planning to set up a prototype to see how RL works, or from a government working  ... 
arXiv:2202.11296v2 fatcat:xdtsmme22rfpfn6rgfotcspnhy

Recurrent Reinforcement Learning: A Hybrid Approach [article]

Xiujun Li, Lihong Li, Jianfeng Gao, Xiaodong He, Jianshu Chen, Li Deng, Ji He
2015 arXiv   pre-print
In this work, we investigate a deep-learning approach to learning the representation of states in partially observable tasks, with minimal prior knowledge of the domain.  ...  The RL component is a deep Q-network (DQN) that learns to optimize the control for maximizing long-term rewards.  ...  ACKNOWLEDGMENTS We thank Nan Jiang for helpful discussions on building the simulator in our experiments.  ... 
arXiv:1509.03044v2 fatcat:ednnw4oa3vds7hurlcgmms5mr4

Visualizing and Understanding Atari Agents [article]

Sam Greydanus, Anurag Koul, Jonathan Dodge, Alan Fern
2018 arXiv   pre-print
In particular, we focus on using saliency maps to understand how an agent learns and executes a policy.  ...  In this paper, we take a step toward explaining deep RL agents through a case study using Atari 2600 environments.  ...  Thanks to James and Judy Greydanus for feedback on early versions of this paper.  ... 
arXiv:1711.00138v5 fatcat:ln6lq4x7kngzrg67fqwqfnq4jq

Hyperparameter Tuning for Deep Reinforcement Learning Applications [article]

Mariam Kiran, Melis Ozyildirim
2022 arXiv   pre-print
In comparison to other neural network architectures, deep RL has not witnessed much hyperparameter tuning, due to its algorithm complexity and simulation platforms needed.  ...  However, setting the right hyperparameters can have a huge impact on the deployed solution performance and reliability in the inference models, produced via RL, used for decision-making.  ...  Our work aims to bridge the gap between deep RL solutions and hyperparameter tuning, showing how HPS-RL can significantly impact RL research and applications being designed in both gaming, simulations,  ... 
arXiv:2201.11182v1 fatcat:ilhx5djtlzbcdcohcax6mj5dda

Deep Q-Networks for Accelerating the Training of Deep Neural Networks [article]

Jie Fu
2017 arXiv   pre-print
With our approach, a deep RL agent (synonym for optimizer in this work) is used to automatically learn policies about how to schedule learning rates during the optimization of a DNN.  ...  As far as we know, this is the first attempt to use deep RL to learn how to optimize a large-sized DNN.  ...  This work is also supported by NUS-Tsinghua Extreme Search (NExT) project through the National Research Foundation, Singapore.  ... 
arXiv:1606.01467v10 fatcat:dckkddh6ifc2lbmcyi3vlkxxqy

An Introduction to Deep Reinforcement Learning

Vincent François-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare, Joelle Pineau
2018 Foundations and Trends® in Machine Learning  
Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the reader is familiar with basic machine learning concepts.  ...  Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more.  ...  We provide descriptions of how deep RL can be used in these settings. In Chapter 11, we present broader perspectives on deep RL.  ... 
doi:10.1561/2200000071 fatcat:gh3odyludnc43oeiqrgrtaer3u

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost [article]

Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine and Vikash Kumar
2018 arXiv   pre-print
that direct deep RL training in the real world is a viable and practical alternative to simulation and model-based control.  ...  In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands.  ...  In this work, we demonstrate that this algorithm provides a practical and useful way of accelerating deep RL on real hardware to solve challenging manipulation problems. VI.  ... 
arXiv:1810.06045v1 fatcat:h5dm7rvxj5h5lgkihznx6yelhu

Stock Market Prediction and Investment using Deep Reinforcement Learning- a Continuous Training Pipeline

2020 International Journal of Engineering and Advanced Technology  
With the latest advancement in Deep Reinforcement Learning, successive practical problems can be modeled and solved with human level accuracy.  ...  In this paper, an agent-based Deep Deterministic Policy Gradient system is proposed to imitate professional trading strategies which is a state-of-the-art framework that can predict and make investment  ...  We also compare other RL algorithms over DDPG to show how it outperforms any other RL algorithm in the stock market domain.At the end we have concluded with the outcomes, advantages, disadvantages and  ... 
doi:10.35940/ijeat.b2034.1210220 fatcat:eksgsnx4hrb5flsqpbxo6dabc4

Machine versus Human Attention in Deep Reinforcement Learning Tasks [article]

Sihang Guo, Ruohan Zhang, Bo Liu, Yifeng Zhu, Mary Hayhoe, Dana Ballard, Peter Stone
2021 arXiv   pre-print
and, 2) How do similarities and differences in these learned representations explain RL agents' performance on these tasks?  ...  In this paper, we shed light on the inner workings of such trained models by analyzing the pixels that they attend to during task execution, and comparing them with the pixels attended to by humans executing  ...  RL versus human attention: Failure states We now turn to the second research question that concerns explainability in deep RL: Why do deep RL agents make mistakes?  ... 
arXiv:2010.15942v3 fatcat:6zt43cylbje4bmzjdbz3a7i32e

Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication [article]

Ali Taleb Zadeh Kasgari, Walid Saad, Mohammad Mozaffari, H. Vincent Poor
2020 arXiv   pre-print
The results also show that the proposed experienced deep-RL framework is able to remove the transient training time that makes conventional deep-RL methods unsuitable for URLLC.  ...  In particular, in order to enable the deep-RL framework to account for extreme network conditions and operate in highly reliable systems, a new approach based on generative adversarial networks (GANs)  ...  To show how the proposed GAN-assisted, experienced deep-RL agent performs, we compare a vanilla deep-RL agent with three pre-trained agents including our experienced deep-RL agent in a wireless environment  ... 
arXiv:1911.03264v2 fatcat:cqr6p3aionfflc4a7py44t3icu

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods [article]

Deirdre Quillen, Eric Jang, Ofir Nachum, Chelsea Finn, Julian Ibarz, Sergey Levine
2018 arXiv   pre-print
Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach  ...  In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping.  ...  While previous works have explored deep reinforcement learning (RL) as a framework for robotic grasping in a sequential decision making context, such studies have been limited to either single objects  ... 
arXiv:1802.10264v2 fatcat:apk5d3vs5ne4zd7xhzcldhzd4e
« Previous Showing results 1 — 15 out of 34,804 results