Filters








478 Hits in 8.2 sec

S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning [article]

Antonin Raffin and Ashley Hill and René Traoré and Timothée Lesort and Natalia Díaz-Rodríguez and David Filliat
<span title="2018-10-10">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper provides a set of environments, data generators, robotic control tasks, metrics and tools to facilitate iterative state representation learning and evaluation in reinforcement learning settings  ...  However, the diversity in applications and methods makes the field lack standard evaluation datasets, metrics and tasks.  ...  Acknowledgments This work is supported by the DREAM project 3 through the European Union Horizon 2020 FET research and innovation program under grant agreement No 640891.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.09369v2">arXiv:1809.09369v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gbp33d7pnzdk7hr27kbebmzxwi">fatcat:gbp33d7pnzdk7hr27kbebmzxwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022002240/https://arxiv.org/pdf/1809.09369v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/ab/c1ab3166336eed0636a10d6b450a014df2f6fd9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.09369v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A deep learning toolbox for noise-optimized, generalized spike inference from calcium imaging data [article]

Peter Rupprecht, Stefano Carta, Adrian Hoffmann, Mayumi Echizen, Kazuo Kitamura, Fritjof Helmchen, Rainer W Friedrich
<span title="2020-09-01">2020</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To optimize performance for unseen imaging data, CASCADE retrains itself by resampling ground truth data to match the respective sampling rate and noise level.  ...  To facilitate routine application of CASCADE we developed systematic performance assessments for unseen data, we openly release all resources, and we provide a user-friendly cloud-based implementation.  ...  We thank Gwendolin Schoenfeld for helpful discussions on dataset 17, and Hendrik Heiser, Nesibe Temiz, Chie Satou, Gwendolin Schoenfeld and Henry Luetcke for testing earlier versions of the toolbox.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2020.08.31.272450">doi:10.1101/2020.08.31.272450</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zmhwqiwdpnbubmdv37m7aphvbi">fatcat:zmhwqiwdpnbubmdv37m7aphvbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108162952/https://www.biorxiv.org/content/biorxiv/early/2020/09/01/2020.08.31.272450.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ab/ef/abef6d434143111435b36f6454067f3f2dec0104.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2020.08.31.272450"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>

Reinforcement Learning for Test Case Prioritization [article]

João Lousada, Miguel Ribeiro
<span title="2020-12-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Additionally, we studied the impact of using Decision Tree (DT) Approximator as a model for memory representation, which failed to produce significant improvements relative to Artificial Neural Networks  ...  This paper extends recent studies on applying Reinforcement Learning to optimize testing strategies.  ...  These estimates are calculated by defining a value-function v π (s), where s is the state, with respect to the learned policy π and can be learned from experience.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.11364v1">arXiv:2012.11364v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wnfnptdfznberbx44quuv6oj6m">fatcat:wnfnptdfznberbx44quuv6oj6m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201225064039/https://arxiv.org/pdf/2012.11364v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/58/92/58920d84d3cf404191f39c6b2abc47a159dc28ee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.11364v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Time Series Anomaly Detection via Reinforcement Learning-Based Model Selection [article]

Jiuqi Elise Zhang, Di Wu, Benoit Boulet
<span title="2022-05-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Time series anomaly detection is of critical importance for the reliable and efficient operation of real-world systems.  ...  In this work, to harness the benefits of different base models, we assume that a pool of anomaly detection models is accessible and propose to utilize reinforcement learning to dynamically select a candidate  ...  Dataset Description The dataset used for evaluation is Secure Water Treatment (SWaT) Dataset 1 collected by iTrust, Centre for Research in Cyber Security at Singapore University of Technology and Design  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.09884v2">arXiv:2205.09884v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/onqttj7dqjdk7om5f4hp35grsm">fatcat:onqttj7dqjdk7om5f4hp35grsm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220525120139/https://arxiv.org/pdf/2205.09884v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/51/b9/51b9a3511970dfb50fed4b1da24ca4437e6c01ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.09884v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Towards automated joining element design

Derk Hendrik Dominick Eggink, Marco Wilhelm Groll, Daniel F. Perez-Ramirez, Johannes Biedert, Christoph Knödler, Patrick Papentin
<span title="">2019</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cx3f4s3qmfe6bg4qvuy2cxezyu" style="color: black;">Procedia Computer Science</a> </i> &nbsp;
Product variety and its induced manufacturing complexity remains to increase and therefore greatens challenges for design of joining elements.  ...  Abstract Product variety and its induced manufacturing complexity remains to increase and therefore greatens challenges for design of joining elements.  ...  Lastly, FE analyses are evaluated and the results are aggregated into a reward for the RL to learn from.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.procs.2019.09.163">doi:10.1016/j.procs.2019.09.163</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fe5ijickbvhxjlolsjsy4f576a">fatcat:fe5ijickbvhxjlolsjsy4f576a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508022503/https://ris.utwente.nl/ws/files/150900200/1_s2.0_S1877050919313419_main.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e7/09/e709739d86defdf38f5426cbe01c3b9e29637c86.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.procs.2019.09.163"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Deep unsupervised state representation learning with robotic priors: a robustness analysis

Timothee Lesort, Mathieu Seurin, Xinrui Li, Natalia Diaz-Rodriguez, David Filliat
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qm5nunzmyva4tfjekdcm34uvhq" style="color: black;">2019 International Joint Conference on Neural Networks (IJCNN)</a> </i> &nbsp;
Deep unsupervised state representation learning with robotic priors: a robustness analysis.  ...  ACKNOWLEDGMENT We thank Clement Masson and Alexandre Coninx, for generating the data and reproducing the dataset in [1] , respectively, as well as for fruitful discussions.  ...  This work is supported by the DREAM project through the European Union Horizon 2020 research and innovation program under grant agreement No 640891.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ijcnn.2019.8852042">doi:10.1109/ijcnn.2019.8852042</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcnn/LesortSLRF19.html">dblp:conf/ijcnn/LesortSLRF19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cp5klo6dnrdy7m4cdkmmg4opdq">fatcat:cp5klo6dnrdy7m4cdkmmg4opdq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508191700/https://hal.archives-ouvertes.fr/hal-02381375/document" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5d/e8/5de89800caabb3628b41450e14133a8412422ed8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ijcnn.2019.8852042"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Explainability in Deep Reinforcement Learning [article]

Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez
<span title="2020-12-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, assessing how XAI techniques can help understand models beyond classification tasks, e.g. for reinforcement learning (RL), has not been extensively studied.  ...  We evaluate mainly studies directly linking explainability to RL, and split these into two categories according to the way the explanations are generated: transparent algorithms and post-hoc explainaility  ...  We also would like to thank Frédéric Herbreteau and Adrien Bennetot for their help and support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.06693v4">arXiv:2008.06693v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r62o6dabufc4ddfklhjx3lgjnq">fatcat:r62o6dabufc4ddfklhjx3lgjnq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827115451/https://arxiv.org/pdf/2008.06693v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.06693v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators [article]

Shreshth Tuli, Rajas Bansal, Rohan Paul, Mausam
<span title="2021-05-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
TANGO encodes the world state, comprising objects and symbolic relationships between them, using a graph neural network.  ...  We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments.  ...  Anil Sharma at VR Lab for compute resources.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.04556v2">arXiv:2105.04556v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2z5x475aebd7tklvms76oh5ot4">fatcat:2z5x475aebd7tklvms76oh5ot4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210513145720/https://arxiv.org/pdf/2105.04556v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/71/15/7115a573ecfeca88edbe622dcf89df9dc8a4340f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.04556v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Reinforcement Learning in Practice: Opportunities and Challenges [article]

Yuxi Li
<span title="2022-04-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this article, we first give a brief introduction to reinforcement learning (RL), and its relationship with deep learning, machine learning and AI.  ...  Then we discuss challenges, in particular, 1) foundation, 2) representation, 3) reward, 4) exploration, 5) model, simulation, planning, and benchmarks, 6) off-policy/offline learning, 7) learning to learn  ...  Different from supervised learning with labelled data, datasets for RL need states/observations, actions and rewards.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11296v2">arXiv:2202.11296v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xdtsmme22rfpfn6rgfotcspnhy">fatcat:xdtsmme22rfpfn6rgfotcspnhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220426140729/https://arxiv.org/pdf/2202.11296v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6d/0a/6d0adac188152fbaa45a88ba4da788926ed8144a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11296v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Reinforcement Learning for Visual Object Tracking in Videos [article]

Da Zhang, Hamid Maei, Xin Wang, Yuan-Fang Wang
<span title="2017-04-10">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Based on this intuition, we formulate our model as a recurrent convolutional neural network agent that interacts with a video overtime, and our model can be trained with reinforcement learning (RL) algorithms  ...  The proposed tracking algorithm achieves state-of-the-art performance in an existing tracking benchmark and operates at frame-rates faster than real-time.  ...  network and RL can be further explored.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.08936v2">arXiv:1701.08936v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/csvjdoftvffrrnrsvtvpkpcq6u">fatcat:csvjdoftvffrrnrsvtvpkpcq6u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830215858/https://arxiv.org/pdf/1701.08936v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/e7/9ce7b6b649a7cf7d0b502ece94cc7ac30991a5bb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.08936v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning [chapter]

Shanhui Sun, Jing Hu, Mingqing Yao, Jinrong Hu, Xiaodong Yang, Qi Song, Xi Wu
<span title="">2019</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The crucial components of a conventional image registration method are the choice of the right feature representations and similarity measures.  ...  The advantage of this algorithm is fully demonstrated by our superior performance on clinical MR and CT image pairs to other state-of-the-art medical image registration methods.  ...  Evaluation and Results We evaluated the models and inference variants (w/o MC) on datasets E 1 and E 2 , respectively. Table 2 summarizes the quantitative results.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-20890-5_33">doi:10.1007/978-3-030-20890-5_33</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pmdhq3khvzf73ew4e6t5qwyhry">fatcat:pmdhq3khvzf73ew4e6t5qwyhry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321143557/https://arxiv.org/pdf/2002.03733v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-20890-5_33"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

The Role of Tactile Sensing in Learning and Deploying Grasp Refinement Algorithms [article]

Alexander Koenig, Zixi Liu, Lucas Janson, Robert Howe
<span title="2022-03-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper uses simulated tactile signals and the reinforcement learning (RL) framework to study the sensing needs in grasping systems.  ...  decrease of at most 6.6% for no tactile sensing in the state.  ...  We found that the rich body of research in grasp analysis is a valuable toolbox to construct meaningful and sound optimization objectives for RL.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.11234v2">arXiv:2109.11234v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hra3yrwdezdebhuf3v4plcf7zi">fatcat:hra3yrwdezdebhuf3v4plcf7zi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210925121345/https://arxiv.org/pdf/2109.11234v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1c/d9/1cd92af532b763ab5a0f661efe17cb630a3f38ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.11234v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Dynamic Belief Graphs to Generalize on Text-Based Games [article]

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton
<span title="2021-05-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text.  ...  Our work demonstrates that the learned graph-based representations help agents converge to better policies than their text-only counterparts and facilitate effective generalization across game configurations  ...  Acknowledgements We thank Alessandro Sordoni and Devon Hjelm for the helpful discussions about the probing task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.09127v4">arXiv:2002.09127v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qahpbnzabzeafdxg4d2fk2mauq">fatcat:qahpbnzabzeafdxg4d2fk2mauq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210513050827/https://arxiv.org/pdf/2002.09127v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/15/b9/15b91292ba80adaa87361a0e8894e47899f02f1d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.09127v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning [article]

Grace W. Lindsay, Josh Merel, Tom Mrsic-Flogel, Maneesh Sahani
<span title="2022-02-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, we compare the representations learned by the RL agent to neural activity from mouse visual cortex and find it to perform as well or better than other models.  ...  Using metrics inspired by the neuroscience literature, we find that the model trained with reinforcement learning has a sparse and high-dimensional representation wherein individual images are represented  ...  Thanks also to Razia Ahamed and Amy Merrick for their work on contract negotiations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02027v2">arXiv:2112.02027v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g6fwjcz5w5e3zjbxgvkmxkffza">fatcat:g6fwjcz5w5e3zjbxgvkmxkffza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220210002743/https://arxiv.org/pdf/2112.02027v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e1/8a/e18af058bd5e3f9ac0e807369f0185ae9d365c7d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02027v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Safety-Critical Driving Scenario Generation – A Methodological Perspective [article]

Wenhao Ding, Chejian Xu, Mansur Arief, Haohong Lin, Bo Li, Ding Zhao
<span title="2022-02-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
One critical challenge for their massive deployment in the real world is their safety evaluation.  ...  Then, we discuss useful tools for scenario generation, including simulation platforms and packages.  ...  CommonRoad [83] is a simulator and an open-source toolbox to train and evaluate RL-based motion planners for autonomous vehicles. Scenario configurations are written in XML files.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.02215v4">arXiv:2202.02215v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uxcvqxk6qna5jh53dwdwqanc4q">fatcat:uxcvqxk6qna5jh53dwdwqanc4q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220516115852/https://arxiv.org/pdf/2202.02215v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/50/2f50c5d72498d00c175e078eff26762562a1e36d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.02215v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 478 results