世界模型 - arXivDaily 专题

2004.06843 2020-04-21 cs.LG stat.ML 50%

Bayesian differential programming for robust systems identification under uncertainty

Yibo Yang, Mohamed Aziz Bhouri, Paris Perdikaris

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

Comments 22 pages, 12 figures

2004.03762 2020-04-09 cs.CL cs.AI 50%

Generating Narrative Text in a Switching Dynamical System

Noah Weber, Leena Shekhar, Heeyoung Kwon, Niranjan Balasubramanian, Nathanael Chambers

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

2003.10520 2020-04-02 cs.AI 50%

Neural Game Engine: Accurate learning of generalizable forward models from pixels

Chris Bamford, Simon Lucas

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

2003.01086 2020-03-03 cs.LG cs.SY eess.SY stat.ML 50%

Predictive Coding for Locally-Linear Control

Rui Shu, Tung Nguyen, Yinlam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung H. Bui

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

1912.10329 2020-02-25 cs.LG stat.ML 50%

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning

Yanchao Sun, Furong Huang

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

Comments To be published in proceedings of AAMAS 2020

1812.10613 2020-01-03 cs.LG cs.IR stat.ML 50%

Generative Adversarial User Model for Reinforcement Learning Based Recommendation System

Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, Le Song

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

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:1052-1061, 2019

1907.04662 2019-12-20 cs.LG stat.ML 50%

An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies

Mirco Mutti, Marcello Restelli

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

Comments In 34th AAAI Conference on Artificial Intelligence (AAAI 2020)

1912.06760 2019-12-17 cs.LG stat.ML 50%

Bayesian Linear Regression on Deep Representations

John Moberg, Lennart Svensson, Juliano Pinto, Henk Wymeersch

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

Comments 4th workshop on Bayesian Deep Learning (NeurIPS 2019), Vancouver, Canada

1912.02644 2019-12-06 stat.ML cs.LG 50%

Representing Closed Transformation Paths in Encoded Network Latent Space

Marissa Connor, Christopher Rozell

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

Comments Accepted at AAAI 2020

1910.04417 2019-11-19 cs.LG cs.AI cs.RO stat.ML 50%

Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement

Chao Yang, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu, Junzhou Huang, Chuang Gan

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

Comments Accepted to NeurIPS 2019 as a spotlight. Chao Yang and Xiaojian Ma contributed equally to this work

1911.03667 2019-11-13 cs.LG eess.SP stat.ML 50%

Factored Latent-Dynamic Conditional Random Fields for Single and Multi-label Sequence Modeling

Satyajit Neogi, Justin Dauwels

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

Comments To be submitted to Journal of Machine Learning Research (JMLR)

1910.12469 2019-10-29 cs.LG stat.ML 50%

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

Qitian Wu, Zixuan Zhang, Xiaofeng Gao, Junchi Yan, Guihai Chen

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

1905.10994 2019-10-25 stat.ML cs.LG 50%

ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks

Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki

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

1909.09734 2019-09-24 stat.ML cs.LG 50%

Particle Smoothing Variational Objectives

Antonio Khalil Moretti, Zizhao Wang, Luhuan Wu, Iddo Drori, Itsik Pe'er

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

Comments 13 pages, 5 figures

1712.04609 2019-09-04 q-fin.CP cs.LG 50%

QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds

Igor Halperin

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

Comments 30 pages (minor changes in the presentation, updated references)

1908.07896 2019-08-23 cs.LG cs.NE 50%

Enabling hyperparameter optimization in sequential autoencoders for spiking neural data

Mohammad Reza Keshtkaran, Chethan Pandarinath

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

1908.03309 2019-08-12 cs.MA cs.CY cs.LG 50%

Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model

Dongjun Kim, Tae-Sub Yun, Il-Chul Moon

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

Comments 31 pages, 12 figures, Journal of Autonomous Agents and Multi-Agent Systems

1907.08461 2019-07-22 cs.LG stat.ML 50%

Delegative Reinforcement Learning: learning to avoid traps with a little help

Vanessa Kosoy

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

Comments 22 pages

Journal ref SafeML ICLR 2019 Workshop

1907.00650 2019-07-02 cs.LG q-bio.NC stat.ML 50%

Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networks

Qi She, Anqi Wu

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

Comments 11 pages, 3 figures, 7 Tables, accepted to The Conference on Uncertainty in Artificial Intelligence (UAI), 2019

1906.08312 2019-06-21 cs.LG stat.ML 50%

Calibrated Model-Based Deep Reinforcement Learning

Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon

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

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4314-4323, 2019

1905.12434 2019-05-30 stat.ML cs.LG 50%

Switching Linear Dynamics for Variational Bayes Filtering

Philip Becker-Ehmck, Jan Peters, Patrick van der Smagt

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

Comments Appears in Proceedings of the 36th International Conference on Machine Learning (ICML)

1905.00475 2019-05-03 cs.LG stat.ML 50%

Efficient Model-free Reinforcement Learning in Metric Spaces

Zhao Song, Wen Sun

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

1811.12165 2019-05-03 cs.SI cs.AI cs.CY 50%

Graph based Entropy for Detecting Explanatory Signs of Changes in Market

Yukio Ohsawa

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

Comments 21 pages, 7 figures, 2 Tables. Copyright remains with the author

Journal ref Rev Socionetwork Strat (2018)

1809.11169 2019-04-19 cs.AI cs.LG cs.RO 50%

Propagation Networks for Model-Based Control Under Partial Observation

Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, Russ Tedrake

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

Comments Accepted to ICRA 2019. Project Page: http://propnet.csail.mit.edu Video: https://youtu.be/ZAxHXegkz48

1805.10755 2019-04-09 cs.LG stat.ML 50%

Dual Policy Iteration

Wen Sun, Geoffrey J. Gordon, Byron Boots, J. Andrew Bagnell

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

Comments NeurIPS 2018; Additional related works

1809.08875 2019-03-15 cs.CV 50%

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling

Judith Bütepage, Hedvig Kjellström, Danica Kragic

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

1903.05136 2019-03-14 cs.CV cs.AI cs.LG 50%

Unsupervised Discovery of Parts, Structure, and Dynamics

Zhenjia Xu, Zhijian Liu, Chen Sun, Kevin Murphy, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

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

Comments ICLR 2019. The first two authors contributed equally to this work

1903.03064 2019-03-08 cs.LG stat.ML 50%

RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems

Ekaterina Abramova, Luke Dickens, Daniel Kuhn, Aldo Faisal

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

Comments 33 pages, 8 figures

1901.08486 2019-01-25 cs.LG cs.AI cs.CV 50%

Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow

Hsuan-Kung Yang, Po-Han Chiang, Kuan-Wei Ho, Min-Fong Hong, Chun-Yi Lee

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

1812.03399 2018-12-11 cs.LG stat.ML 50%

Efficient transfer learning and online adaptation with latent variable models for continuous control

Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos

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

Comments Presented at Continual Learning Workshop, NeurIPS 2018, Montreal, Canada. 5 pages, 4 figures

1. 模型式强化学习 1124 篇

Bayesian differential programming for robust systems identification under uncertainty

Generating Narrative Text in a Switching Dynamical System

Neural Game Engine: Accurate learning of generalizable forward models from pixels

Predictive Coding for Locally-Linear Control

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning

Generative Adversarial User Model for Reinforcement Learning Based Recommendation System

An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies

Bayesian Linear Regression on Deep Representations

Representing Closed Transformation Paths in Encoded Network Latent Space

Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement

Factored Latent-Dynamic Conditional Random Fields for Single and Multi-label Sequence Modeling

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks

Particle Smoothing Variational Objectives

QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds

Enabling hyperparameter optimization in sequential autoencoders for spiking neural data

Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model

Delegative Reinforcement Learning: learning to avoid traps with a little help

Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networks

Calibrated Model-Based Deep Reinforcement Learning

Switching Linear Dynamics for Variational Bayes Filtering

Efficient Model-free Reinforcement Learning in Metric Spaces

Graph based Entropy for Detecting Explanatory Signs of Changes in Market

Propagation Networks for Model-Based Control Under Partial Observation

Dual Policy Iteration

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling

Unsupervised Discovery of Parts, Structure, and Dynamics

RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems

Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow

Efficient transfer learning and online adaptation with latent variable models for continuous control