世界模型 - arXivDaily 专题

2011.06464 2020-12-29 cs.RO cs.AI cs.CV cs.LG 56%

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators

Hsiao-Yu Fish Tung, Zhou Xian, Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki

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

2010.04279 2020-12-23 cs.LG cs.AI 56%

Trajectory Inspection: A Method for Iterative Clinician-Driven Design of Reinforcement Learning Studies

Christina X. Ji, Michael Oberst, Sanjat Kanjilal, David Sontag

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

Comments To appear in AMIA 2021 virtual informatics summit

2005.13239 2020-11-24 cs.LG cs.AI stat.ML 56%

MOPO: Model-based Offline Policy Optimization

Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma

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

Comments NeurIPS 2020. First two authors contributed equally. Last two authors advised equally

2011.00825 2020-11-03 cs.LG cs.AI 56%

Reinforcement Learning with Efficient Active Feature Acquisition

Haiyan Yin, Yingzhen Li, Sinno Jialin Pan, Cheng Zhang, Sebastian Tschiatschek

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

1909.04115 2020-10-20 cs.LG cs.AI stat.ML 56%

Gradient-Aware Model-based Policy Search

Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli

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

2010.05545 2020-10-13 cs.LG cs.AI stat.ML 56%

Local Search for Policy Iteration in Continuous Control

Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz, Josh Merel, Arunkumar Byravan, Abbas Abdolmaleki, Jackie Kay, Jonas Degrave, Julian Schrittwieser, Yuval Tassa, Jonas Buchli, Dan Belov, Martin Riedmiller

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

2007.05896 2020-07-14 cs.LG cs.AI stat.ML 56%

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang

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

2006.04802 2020-06-30 cs.LG stat.ML 56%

Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors

Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna

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

Comments ICML BIG Workshop 2020, camera ready version

2006.05443 2020-06-25 cs.LG cs.AI stat.ML 56%

Variational Model-based Policy Optimization

Yinlam Chow, Brandon Cui, MoonKyung Ryu, Mohammad Ghavamzadeh

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

2006.09919 2020-06-18 cs.LG cs.AI stat.ML 56%

Green Simulation Assisted Reinforcement Learning with Model Risk for Biomanufacturing Learning and Control

Hua Zheng, Wei Xie, Mingbin Ben Feng

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

Comments 12 pages, 1 figures. To appear in the Proceedings of the 2020 Winter Simulation Conference (WSC)

2005.08068 2020-05-19 cs.LG cs.AI stat.ML 56%

Model-Augmented Actor-Critic: Backpropagating through Paths

Ignasi Clavera, Violet Fu, Pieter Abbeel

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

Comments Accepted paper at ICLR 2020

1907.01657 2020-02-18 cs.LG cs.RO stat.ML 56%

Dynamics-Aware Unsupervised Discovery of Skills

Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar, Karol Hausman

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

2002.05822 2020-02-17 cs.LG cs.AI stat.ML 56%

Frequency-based Search-control in Dyna

Yangchen Pan, Jincheng Mei, Amir-massoud Farahmand

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

Comments Accepted to ICLR 2020

1909.01506 2020-02-12 cs.LG stat.ML 56%

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

Nir Levine, Yinlam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui

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

1905.01072 2020-01-27 cs.LG cs.AI stat.ML 56%

Deep Residual Reinforcement Learning

Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson

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

Comments AAMAS 2020

1903.11981 2019-12-30 cs.LG cs.RO stat.ML 56%

Regularizing Trajectory Optimization with Denoising Autoencoders

Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola

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

Comments NeurIPS 2019

1905.12425 2019-12-12 cs.LG cs.AI cs.GT stat.ML 56%

Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities

Aristide Tossou, Debabrota Basu, Christos Dimitrakakis

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

Comments the algorithm has been simplified (no need to look at lower bound of the reward and transitions). Proof has been significantly clean-up. The previous "assumption" is clarified as a condition of the algorithm well-known as sub-modularity. The proof that the bounds satisfy the submodularity is clean-up

1911.10601 2019-11-26 cs.LG cs.AI cs.IT cs.SY eess.SY math.IT stat.ML 56%

Scaling active inference

Alexander Tschantz, Manuel Baltieri, Anil. K. Seth, Christopher L. Buckley

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

1909.09186 2019-09-23 cs.LG cs.AI 56%

Revisit Policy Optimization in Matrix Form

Sitao Luan, Xiao-Wen Chang, Doina Precup

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

1909.07373 2019-09-18 cs.LG cs.AI stat.ML 56%

Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space

Zac Wellmer, James Kwok

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

Comments Published at ECML PKDD 2019

1906.07791 2019-07-05 cs.LG cs.AI stat.ML 56%

Hill Climbing on Value Estimates for Search-control in Dyna

Yangchen Pan, Hengshuai Yao, Amir-massoud Farahmand, Martha White

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

Comments IJCAI 2019

1906.10717 2019-06-27 cs.LG math.OC stat.ML 56%

Uncertainty-aware Model-based Policy Optimization

Tung-Long Vuong, Kenneth Tran

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

1905.13320 2019-06-03 cs.LG cs.AI stat.ML 56%

Combating the Compounding-Error Problem with a Multi-step Model

Kavosh Asadi, Dipendra Misra, Seungchan Kim, Michel L. Littman

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

1811.11067 2019-01-17 cs.LG cs.AI stat.ML 56%

Learning State Representations in Complex Systems with Multimodal Data

Pavel Solovev, Vladimir Aliev, Pavel Ostyakov, Gleb Sterkin, Elizaveta Logacheva, Stepan Troeshestov, Roman Suvorov, Anton Mashikhin, Oleg Khomenko, Sergey I. Nikolenko

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

Comments Fixed references

1901.01977 2019-01-09 cs.LG cs.AI stat.ML 56%

Accelerating Goal-Directed Reinforcement Learning by Model Characterization

Shoubhik Debnath, Gaurav Sukhatme, Lantao Liu

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

Comments The paper was published in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

1901.01325 2019-01-08 cs.LG cs.AI 56%

Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning

Roi Ceren

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

Comments Phd thesis, University of Georgia (2018)

1708.00133 2018-12-07 cs.CL cs.AI cs.LG 56%

Grounding Language for Transfer in Deep Reinforcement Learning

Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

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

Comments JAIR 2018

1801.09624 2018-06-12 cs.LG 56%

Learning the Reward Function for a Misspecified Model

Erik Talvitie

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

Comments To appear at ICML 2018

1805.05935 2018-05-16 cs.AI cs.LG math.OC 56%

Feedback-Based Tree Search for Reinforcement Learning

Daniel R. Jiang, Emmanuel Ekwedike, Han Liu

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

Comments 19 pages, to be presented at ICML 2018

1611.07078 2017-08-18 cs.AI cs.LG stat.ML 56%

A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games

Felix Leibfried, Nate Kushman, Katja Hofmann

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

Comments Presented at the ICML 2017 Workshop on Principled Approaches to Deep Learning, Sydney, Australia, 2017

1. 模型式强化学习 1126 篇

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators

Trajectory Inspection: A Method for Iterative Clinician-Driven Design of Reinforcement Learning Studies

MOPO: Model-based Offline Policy Optimization

Reinforcement Learning with Efficient Active Feature Acquisition

Gradient-Aware Model-based Policy Search

Local Search for Policy Iteration in Continuous Control

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors

Variational Model-based Policy Optimization

Green Simulation Assisted Reinforcement Learning with Model Risk for Biomanufacturing Learning and Control

Model-Augmented Actor-Critic: Backpropagating through Paths

Dynamics-Aware Unsupervised Discovery of Skills

Frequency-based Search-control in Dyna

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

Deep Residual Reinforcement Learning

Regularizing Trajectory Optimization with Denoising Autoencoders

Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities

Scaling active inference

Revisit Policy Optimization in Matrix Form

Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space

Hill Climbing on Value Estimates for Search-control in Dyna

Uncertainty-aware Model-based Policy Optimization

Combating the Compounding-Error Problem with a Multi-step Model

Learning State Representations in Complex Systems with Multimodal Data

Accelerating Goal-Directed Reinforcement Learning by Model Characterization

Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning

Grounding Language for Transfer in Deep Reinforcement Learning

Learning the Reward Function for a Misspecified Model

Feedback-Based Tree Search for Reinforcement Learning

A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games