Filters








188,859 Hits in 4.4 sec

Abstraction Selection in Model-based Reinforcement Learning

Nan Jiang, Alex Kulesza, Satinder P. Singh
2015 International Conference on Machine Learning  
State abstractions are often used to reduce the complexity of model-based reinforcement learning when only limited quantities of data are available.  ...  available abstraction and is polynomial in planning horizon.  ...  Reduction to Offline Policy Evaluation Inspired by model selection techniques in supervised learning, abstractions can also be selected using a crossvalidation procedure: if a second dataset D is given  ... 
dblp:conf/icml/JiangKS15 fatcat:7lnu2qhw6fhlfboemeh2m4zgj4

A Text Abstraction Summary Model Based on BERT Word Embedding and Reinforcement Learning

Qicai Wang, Peiyu Liu, Zhenfang Zhu, Hongxia Yin, Qiuyue Zhang, Lindong Zhang
2019 Applied Sciences  
Finally, the extraction network and the abstraction network are bridged by reinforcement learning.  ...  On this basis we propose a novel hybrid model of extractive-abstractive to combine BERT (Bidirectional Encoder Representations from Transformers) word embedding with reinforcement learning.  ...  Reference [3] used reinforcement learning for ranking sentences in pure extraction-based summarization.  ... 
doi:10.3390/app9214701 fatcat:bv5obrrltfcjxjyd6twklb2zku

Learning Representations in Model-Free Hierarchical Reinforcement Learning

Jacob Rafati, David C. Noelle
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Hierarchical Reinforcement Learning (HRL) methods attempt to address this scalability issue by learning action selection policies at multiple levels of temporal abstraction.  ...  When combined with an intrinsic motivation learning mechanism, this method learns subgoals and skills together, based on experiences in the environment.  ...  In our previous work, we have studied methods for learning such internal representations during model-free reinforcement learning (Rafati and Noelle 2015; .  ... 
doi:10.1609/aaai.v33i01.330110009 fatcat:6fcb3dzfuvdevab7i6v5gito5y

Composable Modular Reinforcement Learning

Christopher Simpkins, Charles Isbell
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Truly modular reinforcement learning would support not only decomposition into modules, but composability of separately written modules in new modular reinforcement learning agents.  ...  This performance degradation means that separately written modules cannot be composed in new modular reinforcement learning agents as-is – they may need to be modified to align their reward scales.  ...  Scholz and colleagues developed Physics-Based Reinforcement Learning (Scholz et al. 2014) , which uses computational physics engines such as Box2D (Catto 2013) as model representations, resulting in  ... 
doi:10.1609/aaai.v33i01.33014975 fatcat:5jtrdgdfkjhfnnv26kuk7gbpta

Why Do Individuals Seek Information? A Selectionist Perspective

Matthias Borgstede
2021 Frontiers in Psychology  
The MLBS has been introduced recently as a formal theory of behavioral selection that links reinforcement learning to natural selection within a single unified model.  ...  Thus, if reinforcement learning is understood as a selection process, there is no need to assume an active agent with an innate tendency to seek information or minimize surprise.  ...  The MLBS has been introduced recently as a formal theory of behavioral selection that links reinforcement learning to natural selection within a single unified model.  ... 
doi:10.3389/fpsyg.2021.684544 pmid:34867580 pmcid:PMC8639505 fatcat:wm7zt54nmvao5pelv6bxnypzru

Hybrid Summarization with Semantic Weighting Reward and Latent Structure Detector

Mingyang Song, Liping Jing, Yi Feng, Zhiwei Sun, Lin Xiao
2021 Asian Conference on Machine Learning  
Therefore, only depending on ROUGE-based reward to optimize the reinforced summarization models may lead to biased summary generation.  ...  However, the reinforced summarization models mainly depend on the ROUGE-based reward, which only has the ability to quantify the extent of wordmatching rather than semantic-matching between document and  ...  In this paper, we focus on reinforcement learning based two-stage abstractive summarization.  ... 
dblp:conf/acml/SongJFSX21 fatcat:xxzu4pum5vfxdhjvs6ub27o7rm

MODEL-FREE INTELLIGENT CONTROL USING REINFORCEMENT LEARNING AND TEMPORAL ABSTRACTION-APPLIED TO pH CONTROL

S. Syafiie, F. Tadeo, E. Martinez
2005 IFAC Proceedings Volumes  
This article presents a solution to pH control based on model-free intelligent control (MFIC) using reinforcement learning.  ...  In standard reinforcement learning, the interaction between an agent and the environment is based on a fixed time scale: during learning, the agent can select several primitive actions depending on the  ...  Compared to other control techniques based on learning, the reinforcement learning approach to model-free control design has some clear advantages: o It is possible to put in the design of the controller  ... 
doi:10.3182/20050703-6-cz-1902.00242 fatcat:bl7taqi46fho3jj7pqb3or2nva

Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning [article]

Jacob Rafati, David C. Noelle
2019 arXiv   pre-print
Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL).  ...  Additionally, we offer a unified approach to learning representations in model-free HRL.  ...  This approach leads to integration of temporal abstraction and intrinsic motivation learning in deep model-free HRL framework.  ... 
arXiv:1911.10164v1 fatcat:vb3txi4lljd5jczvz4zjyaeldm

An abstract model of the basal ganglia, reward learning and action selection

Pierre Berthet, Anders Lansner
2011 BMC Neuroscience  
We present here an abstract computational model of the Basal Ganglia using reinforcement learning and Bayesian inference.  ...  Reinforcement learning is largely used in computational models in order to reproduce and explain these observations.  ...  We present here an abstract computational model of the Basal Ganglia using reinforcement learning and Bayesian inference.  ... 
doi:10.1186/1471-2202-12-s1-p189 pmcid:PMC3240288 fatcat:hvoexctdlzcztfgjdh4nht262i

Copy or Rewrite: Hybrid Summarization with Hierarchical Reinforcement Learning

Liqiang Xiao, Lu Wang, Hao He, Yaohui Jin
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Moreover, we based on Hierarchical Reinforcement Learning, propose an end-to-end reinforcing method to bridge together the extraction module and rewriting module, which can enhance the cooperation between  ...  Existing methods that adopt an extract-then-abstract strategy have achieved impressive results, yet they suffer from the information loss in the abstraction step because they compress all the selected  ...  Acknowledgements This research is supported in part by National Key Research and Development Program of China under Grant 2018YFC0830400 and National Natural Science Foundation of China under Grant 61575123  ... 
doi:10.1609/aaai.v34i05.6470 fatcat:2xae2buyozaaxfd5jio7gnjlva

Mechanisms of Hierarchical Reinforcement Learning in Cortico-Striatal Circuits 2: Evidence from fMRI

D. Badre, M. J. Frank
2011 Cerebral Cortex  
Results validate key predictions of the models and provide evidence for an individual cortico--striatal circuit for reinforcement learning of hierarchical structure at a specific level of policy abstraction  ...  Mechanisms of hierarchical reinforcement learning in corticostriatal circuits I: computational analysis. 22:509--526), we provide novel neural circuit and algorithmic models of hierarchical cognitive control  ...  D'Esposito who were coauthors along with D.B. on the publication of the original hierarchical learning task reported in Badre et al. (2010) and who consented to our reanalysis of the fMRI data from that  ... 
doi:10.1093/cercor/bhr117 pmid:21693491 pmcid:PMC3278316 fatcat:6xila4hogrgmlcym6lnr3ktabq

Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning [article]

Tongzhou Mu, Kaixiang Lin, Feiyang Niu, Govind Thattai
2022 arXiv   pre-print
We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input.  ...  Unlike prior deep reinforcement learning policies parameterized by an end-to-end black-box graph neural network, our approach disentangles the decision-making process into two steps.  ...  Conclusion In this work, we propose a two-step hybrid policy for graph-based reinforcement learning.  ... 
arXiv:2201.08520v1 fatcat:rm5ql5ikajfjnkup2fpbpwjy3m

Reinforcement learning agents providing advice in complex video games

Matthew E. Taylor, Nicholas Carboni, Anestis Fachantidis, Ioannis Vlahavas, Lisa Torrey
2014 Connection science  
Reinforcement learning transfer using a sparse coded inter-task mapping. In LNAI Post-proceedings of the European Workshop on Multi-agent Systems.  ...  Transfer learning via multiple inter-task mappings.  ...  Transferring instances for model-based reinforcement learning.  ... 
doi:10.1080/09540091.2014.885279 fatcat:ept2qvn4n5aktjv37ty6vk6vwy

Intrusion Detection System for Industrial Internet of Things Based on Deep Reinforcement Learning

Sumegh Tharewal, Mohammed Waseem Ashfaque, Sayyada Sara Banu, Perumal Uma, Samar Mansour Hassen, Mohammad Shabaz, Deepak Kumar Jain
2022 Wireless Communications and Mobile Computing  
and using learning algorithm or learning based on feedback signals, in the lack of guiding knowledge, which is based on the trial-and-error learning model, from the interaction with the environment to  ...  , and RNN, as well as deep reinforcement learning models such as DDQN and DQN.  ...  of largescale original input data into higher-level abstract expressions and utilizing reinforcement learning or learning based on feedback signals, and, in the absence of guiding information, it is based  ... 
doi:10.1155/2022/9023719 fatcat:eqsmqeyh7bg6tlwu2ofxomjqfm

Efficient Skill Learning using Abstraction Selection

George Dimitri Konidaris, Andrew G. Barto
2009 International Joint Conference on Artificial Intelligence  
reinforcement learning domain.  ...  We present an algorithm for selecting an appropriate abstraction when learning a new skill.  ...  Background Reinforcement Learning in Continuous Domains Reinforcement learning algorithms usually (although not necessarily, e.g. policy gradient algorithms, model based methods, etc.) learn by constructing  ... 
dblp:conf/ijcai/KonidarisB09 fatcat:bphg3b2igrgtjc6wciit23u3ki
« Previous Showing results 1 — 15 out of 188,859 results