世界模型 - arXivDaily 专题

2112.04153 2022-07-01 cs.LG cs.AI 56%

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

Angelos Filos, Eszter Vértes, Zita Marinho, Gregory Farquhar, Diana Borsa, Abram Friesen, Feryal Behbahani, Tom Schaul, André Barreto, Simon Osindero

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

Comments The first three authors contributed equally. Accepted at ICML 2022

2206.13452 2022-06-28 cs.LG 56%

Causal Dynamics Learning for Task-Independent State Abstraction

Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, Peter Stone

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

Comments International Conference on Machine Learning 2022 (ICML)

2202.00602 2022-06-20 stat.ML cs.AI cs.LG 56%

Meta-Learning Hypothesis Spaces for Sequential Decision-making

Parnian Kassraie, Jonas Rothfuss, Andreas Krause

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

Comments 23 pages, 11 figures

2205.10736 2022-05-24 cs.LG cs.AI stat.ML 56%

Should Models Be Accurate?

Esra'a Saleh, John D. Martin, Anna Koop, Arash Pourzarabi, Michael Bowling

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

Comments The 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making ( RLDM 2022 )

2110.11236 2022-03-29 cs.LG cs.AI q-bio.NC 56%

Variational Predictive Routing with Nested Subjective Timescales

Alexey Zakharov, Qinghai Guo, Zafeirios Fountas

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

Comments 18 pages, 13 figures

Journal ref Tenth International Conference on Learning Representations (ICLR 2022)

2201.01353 2022-03-22 cs.LG cs.CV cs.SY eess.SY 56%

Linear Variational State-Space Filtering

Daniel Pfrommer, Nikolai Matni

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

Comments 18 pages, 6 figures. Fixed proof in appendix. For associated code, see https://github.com/pfrommerd/variational_state_space_models

2203.05079 2022-03-11 cs.LG cs.AI 56%

SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning

Andrew Chester, Michael Dann, Fabio Zambetta, John Thangarajah

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

Comments 11 pages, 8 figures, 3 tables

2203.01810 2022-03-04 cs.LG cs.AI 56%

Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images

Bang You, Oleg Arenz, Youping Chen, Jan Peters

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

Comments 28 pages, 11 figures, 5 tables

Journal ref Neurocomputing 476(2022)102-114

2202.06036 2022-02-15 cs.LG cs.AI 56%

Neural NID Rules

Luca Viano, Johanni Brea

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

Comments Physical Reasoning and Inductive Biases for the Real World at NeurIPS 2021

2106.11735 2022-01-11 cs.LG cs.AI cs.LO 56%

Lifted Model Checking for Relational MDPs

Wen-Chi Yang, Jean-François Raskin, Luc De Raedt

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

2112.10504 2021-12-21 cs.LG cs.AI 56%

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Zhihai Wang, Jie Wang, Qi Zhou, Bin Li, Houqiang Li

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 AAAI22

2106.10316 2021-12-14 cs.AI cs.LG 56%

Proper Value Equivalence

Christopher Grimm, André Barreto, Gregory Farquhar, David Silver, Satinder Singh

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

Journal ref NeurIPS 2021

1906.08253 2021-11-30 cs.LG cs.AI stat.ML 56%

When to Trust Your Model: Model-Based Policy Optimization

Michael Janner, Justin Fu, Marvin Zhang, Sergey Levine

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

Comments NeurIPS 2019. Code at https://github.com/JannerM/mbpo, project page at: https://jannerm.github.io/mbpo-www/

1903.00715 2021-11-03 cs.LG cs.AI stat.ML 56%

Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning

Ruo-Ze Liu, Haifeng Guo, Xiaozhong Ji, Yang Yu, Zhen-Jia Pang, Zitai Xiao, Yuzhou Wu, Tong Lu

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

2110.15489 2021-11-01 cs.LG cs.AI 56%

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL

Sumedh A Sontakke, Stephen Iota, Zizhao Hu, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf

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

2110.14524 2021-10-28 cs.LG cs.MA 56%

Model based Multi-agent Reinforcement Learning with Tensor Decompositions

Pascal Van Der Vaart, Anuj Mahajan, Shimon Whiteson

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

Journal ref 2nd Workshop on Quantum Tensor Networks in Machine Learning (NeurIPS 2021)

2110.12840 2021-10-26 cs.LG cs.AI stat.ML 56%

Self-Consistent Models and Values

Gregory Farquhar, Kate Baumli, Zita Marinho, Angelos Filos, Matteo Hessel, Hado van Hasselt, David Silver

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

Comments NeurIPS 2021

2110.07910 2021-10-18 cs.LG cs.AI 56%

SaLinA: Sequential Learning of Agents

Ludovic Denoyer, Alfredo de la Fuente, Song Duong, Jean-Baptiste Gaya, Pierre-Alexandre Kamienny, Daniel H. Thompson

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

2102.10242 2021-09-23 cs.CL cs.AI cs.LG 56%

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao, Wei Wei

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

Comments Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021

2109.03214 2021-09-08 cs.LG cs.AI 56%

Robust Predictable Control

Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

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

Comments Project site with videos and code: https://ben-eysenbach.github.io/rpc

2003.01852 2021-08-27 cs.LG cs.RO stat.ML 56%

q-VAE for Disentangled Representation Learning and Latent Dynamical Systems

Taisuke Kobayashi

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

Comments 8 pages, 8 figures

Journal ref IEEE Robotics and Automation Letters, 2020

2010.04444 2021-08-23 cs.LG cs.AI 56%

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

Paul J. Pritz, Liang Ma, Kin K. Leung

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

2106.04799 2021-06-10 cs.LG 56%

Pretraining Representations for Data-Efficient Reinforcement Learning

Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, Devon Hjelm, Philip Bachman, Aaron Courville

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

2011.10605 2021-04-30 cs.LG cs.RO 56%

Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System

Junhyeok Ahn, Luis Sentis

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

Comments Accepted to 2021 L4DC

2104.00163 2021-04-02 cs.LG cs.AI 56%

DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation

Faraz Torabi, Garrett Warnell, Peter Stone

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

2103.10369 2021-03-19 cs.LG cs.AI stat.ML 56%

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning

Sebastian Curi, Ilija Bogunovic, Andreas Krause

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

2005.05951 2021-03-03 cs.LG cs.AI stat.ML 56%

MOReL : Model-Based Offline Reinforcement Learning

Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims

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

Comments First two authors contributed equally. Published at NeurIPS 2020. After publication at NeurIPS 2020, (1) D4RL benchmark results have been added; (2) hyper-parameter ablation studies have been added; (3) scope of Lemma 3 has been extended

1906.09323 2021-01-29 cs.LG cs.AI cs.GT stat.ML 56%

Reinforcement Learning with Convex Constraints

Sobhan Miryoosefi, Kianté Brantley, Hal Daumé, Miroslav Dudik, Robert Schapire

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

Journal ref Advances in Neural Information Processing Systems 32 (2019), 14093-14102

2101.08740 2021-01-22 cs.RO cs.LG cs.SY eess.SY 56%

Model-based Policy Search for Partially Measurable Systems

Fabio Amadio, Alberto Dalla Libera, Ruggero Carli, Daniel Nikovski, Diego Romeres

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

Comments Accepted to 3rd Robot Learning Workshop: Grounding Machine Learning Development in the Real World (NeurIPS 2020)

2010.15948 2021-01-06 cs.RO cs.LG 56%

Bayes-Adaptive Deep Model-Based Policy Optimisation

Tai Hoang, Ngo Anh Vien

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

Comments Source code https://github.com/thobotics/RoMBRL

1. 模型式强化学习 1126 篇

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

Causal Dynamics Learning for Task-Independent State Abstraction

Meta-Learning Hypothesis Spaces for Sequential Decision-making

Should Models Be Accurate?

Variational Predictive Routing with Nested Subjective Timescales

Linear Variational State-Space Filtering

SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning

Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images

Neural NID Rules

Lifted Model Checking for Relational MDPs

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Proper Value Equivalence

When to Trust Your Model: Model-Based Policy Optimization

Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL

Model based Multi-agent Reinforcement Learning with Tensor Decompositions

Self-Consistent Models and Values

SaLinA: Sequential Learning of Agents

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

Robust Predictable Control

q-VAE for Disentangled Representation Learning and Latent Dynamical Systems

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

Pretraining Representations for Data-Efficient Reinforcement Learning

Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System

DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning

MOReL : Model-Based Offline Reinforcement Learning

Reinforcement Learning with Convex Constraints

Model-based Policy Search for Partially Measurable Systems

Bayes-Adaptive Deep Model-Based Policy Optimisation