世界模型 - arXivDaily 专题

2104.02844 2021-04-08 eess.SY cs.AI cs.SY 50%

GEM: Group Enhanced Model for Learning Dynamical Control Systems

Philippe Hansen-Estruch, Wenling Shang, Lerrel Pinto, Pieter Abbeel, Stas Tiomkin

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.AI

Comments 14 pages, 8 figures

2103.16564 2021-03-31 cs.CV cs.AI cs.CL cs.LG cs.SC 50%

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Zhenfang Chen, Jiayuan Mao, Jiajun Wu, Kwan-Yee Kenneth Wong, Joshua B. Tenenbaum, Chuang Gan

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

Comments ICLR 2021. Project page: http://dcl.csail.mit.edu/

2103.09439 2021-03-18 cs.RO cs.AI cs.LG 50%

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

Zhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2103.03385 2021-03-08 cs.LG physics.data-an stat.ML 50%

Gaussian processes meet NeuralODEs: A Bayesian framework for learning the dynamics of partially observed systems from scarce and noisy data

Mohamed Aziz Bhouri, Paris Perdikaris

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments 27 pages, 16 figures, 4 tables. arXiv admin note: text overlap with arXiv:2004.06843

2103.02225 2021-03-04 cs.LG 50%

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

Hongyao Tang, Jianye Hao, Guangyong Chen, Pengfei Chen, Chen Chen, Yaodong Yang, Luo Zhang, Wulong Liu, Zhaopeng Meng

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments Accepted paper on AAAI 2021. arXiv admin note: text overlap with arXiv:1905.11100

2102.08810 2021-02-18 physics.comp-ph cs.CE cs.LG 50%

Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics

Pantelis R. Vlachas, Julija Zavadlav, Matej Praprotnik, Petros Koumoutsakos

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

1909.10863 2021-02-15 cs.AI q-bio.QM 50%

Active inference: demystified and compared

Noor Sajid, Philip J. Ball, Thomas Parr, Karl J. Friston

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.AI

Journal ref Neural Computation 2021

2102.03866 2021-02-09 cs.LG 50%

Model-Augmented Q-learning

Youngmin Oh, Jinwoo Shin, Eunho Yang, Sung Ju Hwang

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2101.01864 2021-01-07 math.DS cs.LG 50%

Constrained Block Nonlinear Neural Dynamical Models

Elliott Skomski, Soumya Vasisht, Colby Wight, Aaron Tuor, Jan Drgona, Draguna Vrabie

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments 10 pages. Submitted to American Control Conference ACC 2020. Under review

2011.07665 2020-11-17 cs.LG 50%

Analog Circuit Design with Dyna-Style Reinforcement Learning

Wook Lee, Frans A. Oliehoek

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments NeurIPS 2020 Workshop on Machine Learning for Engineering Modeling, Simulation and Design

2011.04391 2020-11-10 q-fin.TR cs.LG stat.AP stat.ML 50%

Reinforced Deep Markov Models With Applications in Automatic Trading

Tadeu A. Ferreira

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments 39 pages

2011.03880 2020-11-10 cs.LG stat.ML 50%

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Zijie Huang, Yizhou Sun, Wei Wang

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments Neurips 2020

2011.03615 2020-11-10 cs.LG cs.NI 50%

Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial

Amal Feriani, Ekram Hossain

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2011.01226 2020-11-04 stat.ML cs.LG 50%

Sample-efficient reinforcement learning using deep Gaussian processes

Charles Gadd, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2011.01046 2020-11-03 cs.RO cs.AI cs.LG 50%

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Nan Lin, Yuxuan Li, Yujun Zhu, Ruolin Wang, Xiayu Zhang, Jianmin Ji, Keke Tang, Xiaoping Chen, Xinming Zhang

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2002.05909 2020-10-23 cs.LG nlin.CD physics.data-an q-bio.QM stat.ML 50%

Deep reconstruction of strange attractors from time series

William Gilpin

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments 9 pages, 6 figures, plus appendices

Journal ref NeurIPS (Neural Information Processing Systems) 2020

2010.05673 2020-10-20 cs.LG 50%

Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

Qiwen Cui, Lin F. Yang

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments 30 pages, to appear in NeurIPS2020

1903.01385 2020-10-14 cs.LG stat.ML 50%

Joint Perception and Control as Inference with an Object-based Implementation

Minne Li, Zheng Tian, Pranav Nashikkar, Ian Davies, Ying Wen, Jun Wang

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2010.04870 2020-10-13 cs.LG 50%

Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

Reazul Hasan Russel, Mouhacine Benosman, Jeroen Van Baar

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2007.13699 2020-09-22 cs.AI cs.LG cs.MA cs.SY eess.SY 50%

FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Joint Passengers & Goods Transportation

Kaushik Manchella, Abhishek K. Umrawal, Vaneet Aggarwal

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.MA；dynamics model(abstract)

Comments Accepted to IEEE Transactions on Intelligent Transportation Systems

1903.08772 2020-09-10 cs.AI 50%

ToyArchitecture: Unsupervised Learning of Interpretable Models of the World

Jaroslav Vítků, Petr Dluhoš, Joseph Davidson, Matěj Nikl, Simon Andersson, Přemysl Paška, Jan Šinkora, Petr Hlubuček, Martin Stránský, Martin Hyben, Martin Poliak, Jan Feyereisl, Marek Rosa

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.AI

Comments Revision: changed the pdftitle

2008.07032 2020-08-18 cs.LG stat.ML 50%

Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems

Zhe Chen, Yuyan Wang, Dong Lin, Derek Zhiyuan Cheng, Lichan Hong, Ed H. Chi, Claire Cui

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments 9 pages

2007.07170 2020-08-12 cs.LG cs.AI cs.RO stat.ML 50%

Goal-Aware Prediction: Learning to Model What Matters

Suraj Nair, Silvio Savarese, Chelsea Finn

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

1910.02919 2020-07-14 cs.LG stat.ML 50%

Multi-step Greedy Reinforcement Learning Algorithms

Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments ICML 2020

2007.03742 2020-07-09 cs.LG stat.ML 50%

Meta-active Learning in Probabilistically-Safe Optimization

Mariah L. Schrum, Mark Connolly, Eric Cole, Mihir Ghetiya, Robert Gross, Matthew C. Gombolay

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments 9 pages

1902.07186 2020-07-01 cs.LG q-bio.NC stat.ML 50%

Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI

Georgia Koppe, Hazem Toutounji, Peter Kirsch, Stefanie Lis, Daniel Durstewitz

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

2006.10277 2020-06-19 stat.ML cs.LG math.OC 50%

Active Learning for Nonlinear System Identification with Guarantees

Horia Mania, Michael I. Jordan, Benjamin Recht

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments 29 pages

2002.08243 2020-06-19 cs.LG stat.ML 50%

Optimistic Policy Optimization with Bandit Feedback

Yonathan Efroni, Lior Shani, Aviv Rosenberg, Shie Mannor

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments Accepted to ICML 2020

1811.02459 2020-06-18 stat.ML cs.LG q-bio.NC q-bio.QM 50%

Nonlinear Evolution via Spatially-Dependent Linear Dynamics for Electrophysiology and Calcium Data

Daniel Hernandez, Antonio Khalil Moretti, Ziqiang Wei, Shreya Saxena, John Cunningham, Liam Paninski

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments 8 figs, Accepted at NBDT

2006.02949 2020-06-05 q-bio.NC cs.AI 50%

The growth and form of knowledge networks by kinesthetic curiosity

Dale Zhou, David M. Lydon-Staley, Perry Zurn, Danielle S. Bassett

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.AI

1. 模型式强化学习 1124 篇

GEM: Group Enhanced Model for Learning Dynamical Control Systems

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

Gaussian processes meet NeuralODEs: A Bayesian framework for learning the dynamics of partially observed systems from scarce and noisy data

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics

Active inference: demystified and compared

Model-Augmented Q-learning

Constrained Block Nonlinear Neural Dynamical Models

Analog Circuit Design with Dyna-Style Reinforcement Learning

Reinforced Deep Markov Models With Applications in Automatic Trading

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial

Sample-efficient reinforcement learning using deep Gaussian processes

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Deep reconstruction of strange attractors from time series

Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

Joint Perception and Control as Inference with an Object-based Implementation

Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Joint Passengers & Goods Transportation

ToyArchitecture: Unsupervised Learning of Interpretable Models of the World

Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems

Goal-Aware Prediction: Learning to Model What Matters

Multi-step Greedy Reinforcement Learning Algorithms

Meta-active Learning in Probabilistically-Safe Optimization

Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI

Active Learning for Nonlinear System Identification with Guarantees

Optimistic Policy Optimization with Bandit Feedback

Nonlinear Evolution via Spatially-Dependent Linear Dynamics for Electrophysiology and Calcium Data

The growth and form of knowledge networks by kinesthetic curiosity