1,281 Hits in 12.6 sec

Leveraging human knowledge in tabular reinforcement learning: A study of human subjects [article]

Ariel Rosenfeld, Moshe Cohen, Matthew E. Taylor, Sarit Kraus
2018 arXiv   pre-print
Through this human study, consisting of 51 human participants, we shed new light on the human factors that play a key role in RL.  ...  Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems.  ...  As a result of this addition, we were able to investigate the reward shaping condition, which was not investigated in previous reports, and provide a much broader and in-depth investigation of human designers  ... 
arXiv:1805.05769v1 fatcat:ezenp2mskbhbjf6dgoswgeqrvi

Leveraging Human Knowledge in Tabular Reinforcement Learning: A Study of Human Subjects

Ariel Rosenfeld, Matthew E. Taylor, Sarit Kraus
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems.  ...  knowledge for speeding up tabular RL.  ...  Acknowledgments This paper is an extended version of a short AAMAS paper [Rosenfeld et al., 2017] . This research was funded in part by MAFAT.  ... 
doi:10.24963/ijcai.2017/534 dblp:conf/ijcai/RosenfeldTK17 fatcat:43tmosczu5a2hhord6oo6gtike

Integrating Machine Learning with Human Knowledge

Changyu Deng, Xunbi Ji, Colton Rainey, Jianyu Zhang, Wei Lu
2020 iScience  
This allows leveraging the vast amount of human knowledge and capability of machine learning to achieve functions and performance not available before and will facilitate the interaction between human  ...  Integrating human knowledge into machine learning can significantly reduce data requirement, increase reliability and robustness of machine learning, and build explainable machine learning systems.  ...  A recent work summarizes how to inject human knowledge into a tabular method with reward shaping (Rosenfeld et al., 2018) . In the other way, guidelines from humans directly exist in the policy.  ... 
doi:10.1016/j.isci.2020.101656 pmid:33134890 pmcid:PMC7588855 fatcat:y7r26d6o7jeejm7yxszbtjyuca

Towards Continual Reinforcement Learning: A Review and Perspectives [article]

Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup
2020 arXiv   pre-print
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL.  ...  We begin by discussing our perspective on why RL is a natural fit for studying continual learning.  ...  This work originated as a class project undertaken in the graduate-level course on Continual Learning: Towards "Broad" AI (IFT-6760B) at Mila, Montreal.  ... 
arXiv:2012.13490v1 fatcat:vcleqjnpgrbkvg477d4prmzg2q

Learning Time-Sensitive Strategies in Space Fortress [article]

Akshat Agarwal, Ryan Hope, Katia Sycara
2018 arXiv   pre-print
in Deep Learning for RL.  ...  In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable  ...  The collection of human data and development of the OpenAI Gym interface for Space Fortress was supported by ONR grant N00014-15-1-2151.  ... 
arXiv:1805.06824v4 fatcat:26lb7tt5cfbcdnfsp4tfprxccq

Learning Transferable Concepts in Deep Reinforcement Learning [article]

Diego Gomez, Nicanor Quijano, Luis Felipe Giraldo
2021 arXiv   pre-print
Here, we introduce a new perspective on the problem of leveraging prior knowledge to solve future unknown tasks.  ...  While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a  ...  Deep reinforcement learning methods in the context of multi-task learning.  ... 
arXiv:2005.07870v3 fatcat:xnbbfh4ifzdr3onihe76zndna4

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details.  ...  We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.  ...  Lanctot et al. (2017) observe that independent RL, in which each agent learns by interacting with the environment, oblivious to other agents, can overfit the learned policies to other agents' policies  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning [article]

Abhishek Das, Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra
2017 arXiv   pre-print
We use deep reinforcement learning (RL) to learn the policies of these agents end-to-end -- from pixels to multi-agent multi-round dialog to game reward. We demonstrate two experimental results.  ...  Interestingly, the RL Qbot learns to ask questions that Abot is good at, ultimately resulting in more informative dialog and a better team.  ...  Views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the U.S.  ... 
arXiv:1703.06585v2 fatcat:6gmbr5hcgbhurdapclicxci33q

Exploring Reinforcement Learning For Mobile Percussive Collaboration

Nate Derbinsky, Georg Essl
2012 Zenodo  
We show that reinforcement learning can incrementally learn percussive beat patterns played by humans and supports realtime collaborative performance in the absence of one or more performers.  ...  This work leverages an existing integration between urMus and Soar and addresses multiple challenges involved in the deployment of machine-learning algorithms for mobile music expression, including tradeoffs  ...  If RL succeeds in learning individual percussive policies, we can then apply this learned knowledge to facilitate collaborative performance in the absence of one or more human performers.  ... 
doi:10.5281/zenodo.1178243 fatcat:xnwn27yl5vcuzidys2s2oyvwdy

Adaptive Agents in Minecraft: A Hybrid Paradigm for Combining Domain Knowledge with Reinforcement Learning [chapter]

Priyam Parashar, Bradley Sheneman, Ashok K. Goel
2017 Lecture Notes in Computer Science  
We present a pilot study focused on creating flexible Hierarchical Task Networks which can leverage Reinforcement Learning to repair and adapt incomplete plans in the simulated rich domain of Minecraft  ...  The main aim of our study is to create flexible knowledge-based planners for robots, which can leverage exploration and guide learning more efficiently by imparting structure using domain knowledge.  ...  Reinforcement Learning: Q-learning We have implemented a tabular form of Q-learning for our reinforcement learning purposes in this paper, using the following update formula. s denotes a state from the  ... 
doi:10.1007/978-3-319-71679-4_6 fatcat:i6qfjjl6arejlearxsm5uxwfmq

Teaching on a Budget in Multi-Agent Deep Reinforcement Learning [article]

Ercüment İlhan, Jeremy Gow, Diego Perez-Liebana
2019 arXiv   pre-print
In Multi-Agent Reinforcement Learning (MARL) this drawback becomes worse, but at the same time, a new set of opportunities to leverage knowledge are also presented through agent interactions.  ...  However, studies in this line of research are currently very limited.  ...  Advising Methods in Multi-Agent Reinforcement Learning Application of action advising methods in MARL is a challenging and a fairly new subject.  ... 
arXiv:1905.01357v2 fatcat:kfonuwi3ejduvnfx6i3vxn3azq

Reinforcement Learning-Based School Energy Management System

Yassine Chemingui, Adel Gastli, Omar Ellabban
2020 Energies  
In this work, a Deep Reinforcement Learning agent is proposed for controlling and optimizing a school building's energy consumption.  ...  to the integration of the behavior cloning learning technique.  ...  This study leverages a deep reinforcement learning (DRL) framework to develop an artificially intelligent agent capable of handling the tradeoffs between building indoor comfort and energy consumption.  ... 
doi:10.3390/en13236354 fatcat:b6cp3zxj6jhqxabemo5q6mva6y

Reinforcement Learning Approaches in Social Robotics [article]

Neziha Akalin, Amy Loutfi
2021 arXiv   pre-print
The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view  ...  We present a thorough analysis of reinforcement learning approaches in social robotics.  ...  A personalized policy was trained through 6-8 sessions of interaction by using a tabular Q-learning algorithm. The reward function was a weighted sum of engagement and learning gains of the child.  ... 
arXiv:2009.09689v4 fatcat:6vvotvwfhjh5zbsgzmplj5wq7q

Learning bicycle stunts

Jie Tan, Yuting Gu, C. Karen Liu, Greg Turk
2014 ACM Transactions on Graphics  
We present a general approach for simulating and controlling a human character that is riding a bicycle. The two main components of our system are offline learning and online simulation.  ...  The rider not only learns to steer and to balance in normal riding situations, but also learns to perform a wide variety of stunts, including wheelie, endo, bunny hop, front wheel pivot and back hop.  ...  We want to thank Yuting Ye for her suggestions and all the members of Gatech Graphics Lab for their help on this work. We also want to thank GVU center of Gatech.  ... 
doi:10.1145/2601097.2601121 fatcat:z2ds2yp5tjfkfh3r6ngjbsxo6u

Human-in-the-Loop Methods for Data-Driven and Reinforcement Learning Systems [article]

Vinicius G. Goecks
2020 arXiv   pre-print
Results presented in this work show that the reward signal that is learned based upon human interaction accelerates the rate of learning of reinforcement learning algorithms and that learning from a combination  ...  This research investigates how to integrate these human interaction modalities to the reinforcement learning loop, increasing sample efficiency and enabling real-time reinforcement learning in robotics  ...  A common approach in human-in-the-loop reinforcement learning is modify the reinforcement learning loss function to leverage a human dataset of trajectories to solve the desired task. Hester et al.  ... 
arXiv:2008.13221v1 fatcat:aofoenmwcvckvagbttrkskevty
« Previous Showing results 1 — 15 out of 1,281 results