世界模型 - arXivDaily 专题

2205.15795 2022-06-01 cs.LG 50%

A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud

Siqiao Xue, Chao Qu, Xiaoming Shi, Cong Liao, Shiyi Zhu, Xiaoyu Tan, Lintao Ma, Shiyu Wang, Shijun Wang, Yun Hu, Lei Lei, Yangfei Zheng, Jianguo Li, James Zhang

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

Comments Accepted by KDD'22 Applied Research Track

2105.14108 2022-05-27 cs.AI q-bio.NC 50%

Efficient and robust multi-task learning in the brain with modular latent primitives

Christian David Márton, Léo Gagnon, Guillaume Lajoie, Kanaka Rajan

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

Comments *Shared senior authorship

2112.01506 2022-05-17 cs.LG stat.ML 50%

Sample Complexity of Robust Reinforcement Learning with a Generative Model

Kishan Panaganti, Dileep Kalathil

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

Comments Published in the International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

2203.14660 2022-03-29 cs.LG 50%

Revisiting Model-based Value Expansion

Daniel Palenicek, Michael Lutter, Jan Peters

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

2110.13079 2022-03-22 cs.LG stat.ML 50%

Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks

Giacomo Arcieri, David Wölfle, Eleni Chatzi

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

2110.03244 2022-03-15 cs.LG 50%

Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver

Xiaoyu Chen, Jiachen Hu, Lin F. Yang, Liwei Wang

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

2108.01846 2022-03-14 cs.LG cs.AI cs.RO cs.SY eess.SY 50%

Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Yuping Luo, Tengyu Ma

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

Comments NeurIPS 2021. Source code at https://github.com/roosephu/crabs

2202.08812 2022-02-18 cs.IR cs.LG 50%

Should I send this notification? Optimizing push notifications decision making by modeling the future

Conor O'Brien, Huasen Wu, Shaodan Zhai, Dalin Guo, Wenzhe Shi, Jonathan J Hunt

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

2202.06159 2022-02-17 q-bio.NC cs.LG 50%

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation

Justin Jude, Matthew G Perich, Lee E Miller, Matthias H Hennig

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

2105.11640 2022-02-01 cs.LG cs.SY eess.SY 50%

Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles

Zhaoxuan Zhu, Nicola Pivaro, Shobhit Gupta, Abhishek Gupta, Marcello Canova

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

Comments This work has been submitted to the IEEE for possible publication and is under review. Paper summary: 13 pages, 11 figures

2102.08363 2022-01-28 cs.LG cs.AI cs.RO 50%

COMBO: Conservative Offline Model-Based Policy Optimization

Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn

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

Comments NeurIPS 2021

2112.10264 2021-12-22 cs.LG math.OC math.PR stat.ML 50%

Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models

Lukasz Szpruch, Tanut Treetanthiploet, Yufei Zhang

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

2112.07701 2021-12-16 cs.LG 50%

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

Yecheng Jason Ma, Andrew Shen, Osbert Bastani, Dinesh Jayaraman

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

Comments AAAI 2022

2112.01388 2021-12-03 cs.LG stat.ML 50%

Residual Pathway Priors for Soft Equivariance Constraints

Marc Finzi, Gregory Benton, Andrew Gordon Wilson

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

Comments NeurIPS 2021. Code available at https://github.com/mfinzi/residual-pathway-priors

2010.14685 2021-11-17 physics.comp-ph cs.AI 50%

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

Kookjin Lee, Eric J. Parish

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

2102.06961 2021-11-11 cs.LG 50%

PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators

Anish Agarwal, Abdullah Alomar, Varkey Alumootil, Devavrat Shah, Dennis Shen, Zhi Xu, Cindy Yang

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

2010.08729 2021-11-10 stat.ML cs.LG stat.CO 50%

Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter

Tsuyoshi Ishizone, Tomoyuki Higuchi, Kazuyuki Nakamura

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

2012.14944 2021-11-01 stat.ML cond-mat.stat-mech cs.LG physics.bio-ph physics.data-an 50%

Learning non-stationary Langevin dynamics from stochastic observations of latent trajectories

Mikhail Genkin, Owen Hughes, Tatiana A. Engel

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

Journal ref Nat Commun 12, 5986 (2021)

2110.14853 2021-10-29 q-bio.NC 50%

Targeted Neural Dynamical Modeling

Cole Hurwitz, Akash Srivastava, Kai Xu, Justin Jude, Matthew G. Perich, Lee E. Miller, Matthias H. Hennig

专题命中模型式强化学习：latent dynamics(abstract)；dynamics model(abstract)

2110.14096 2021-10-28 cs.LG cs.AI cs.CV 50%

Towards Robust Bisimulation Metric Learning

Mete Kemertas, Tristan Aumentado-Armstrong

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

Comments Accepted to NeurIPS 2021

2012.08508 2021-10-27 cs.CV cs.AI cs.CL cs.LG 50%

Attention over learned object embeddings enables complex visual reasoning

David Ding, Felix Hill, Adam Santoro, Malcolm Reynolds, Matt Botvinick

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

Comments 22 pages, 5 figures

2108.04899 2021-10-05 cs.LG 50%

Analysis of ODE2VAE with Examples

Batuhan Koyuncu

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

Comments 16 pages, 20 figures, typos corrected

2103.12413 2021-08-18 cs.LG 50%

Neural ODE Processes

Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò

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

Comments ICLR 2021. 9 pages, 6 figures, 7 pages of appendices

2012.02542 2021-08-17 cs.CV 50%

Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

Nando Metzger, Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

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

2107.13790 2021-07-30 cs.LG 50%

Non-Markovian Reinforcement Learning using Fractional Dynamics

Gaurav Gupta, Chenzhong Yin, Jyotirmoy V. Deshmukh, Paul Bogdan

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

Comments 14 pages, 3 figures, CDC2021

2107.11587 2021-07-27 cs.LG 50%

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?

Balázs Kégl, Gabriel Hurtado, Albert Thomas

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

Comments Published at International Conference on Learning Representations, 2021: https://openreview.net/forum?id=p5uylG94S68

2105.03835 2021-06-11 cs.LG 50%

Segmenting Hybrid Trajectories using Latent ODEs

Ruian Shi, Quaid Morris

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

2106.02204 2021-06-07 cs.AI 50%

Detecting and Adapting to Novelty in Games

Xiangyu Peng, Jonathan C. Balloch, Mark O. Riedl

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

Comments 10 pages, 5 figures, Accepted to the AAAI21 Workshop on on Reinforcement Learning in Games

2104.10483 2021-04-23 cs.LG q-fin.MF q-fin.PM 50%

Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting

Eric Benhamou, David Saltiel, Serge Tabachnik, Sui Kai Wong, François Chareyron

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

Comments 8 pages, 10 figures

2104.06358 2021-04-14 cs.LG 50%

Data-Driven Reinforcement Learning for Virtual Character Animation Control

Vihanga Gamage, Cathy Ennis, Robert Ross

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

1. 模型式强化学习 1124 篇

A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud

Efficient and robust multi-task learning in the brain with modular latent primitives

Sample Complexity of Robust Reinforcement Learning with a Generative Model

Revisiting Model-based Value Expansion

Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks

Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver

Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Should I send this notification? Optimizing push notifications decision making by modeling the future

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation

Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles

COMBO: Conservative Offline Model-Based Policy Optimization

Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

Residual Pathway Priors for Soft Equivariance Constraints

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators

Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter

Learning non-stationary Langevin dynamics from stochastic observations of latent trajectories

Targeted Neural Dynamical Modeling

Towards Robust Bisimulation Metric Learning

Attention over learned object embeddings enables complex visual reasoning

Analysis of ODE2VAE with Examples

Neural ODE Processes

Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

Non-Markovian Reinforcement Learning using Fractional Dynamics

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?

Segmenting Hybrid Trajectories using Latent ODEs

Detecting and Adapting to Novelty in Games

Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting

Data-Driven Reinforcement Learning for Virtual Character Animation Control