世界模型 - arXivDaily 专题

2403.06328 2025-01-22 cs.LG 56%

Distributional Successor Features Enable Zero-Shot Policy Optimization

Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta

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

2501.02774 2025-01-07 cs.LG 56%

Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes

Zijian Wang, Bin Wang, Mingwen Shao, Hongbo Dou, Boxiang Tao

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

2412.20537 2024-12-31 cs.LG 56%

Diminishing Return of Value Expansion Methods

Daniel Palenicek, Michael Lutter, João Carvalho, Daniel Dennert, Faran Ahmad, Jan Peters

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

Comments arXiv admin note: substantial text overlap with arXiv:2303.03955

2412.19194 2024-12-30 cs.LG cs.AI 56%

Provably Efficient Exploration in Reward Machines with Low Regret

Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard, Chenxiao Ma, Mohammad Sadegh Talebi

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

Comments 35 pages

1901.07905 2024-12-20 eess.SY cs.SY 56%

Reinforcement Learning Ship Autopilot: Sample efficient and Model Predictive Control-based Approach

Yunduan Cui, Shigeki Osaki, Takamitsu Matsubara

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

Comments The 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

2312.17248 2024-12-10 cs.LG cs.AI cs.CC cs.DS stat.ML 56%

Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity

Guhao Feng, Han Zhong

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

Comments NeurIPS 2024; this updated version includes additional theoretical findings and experimental results

2404.13846 2024-12-04 cs.LG cs.AI cs.CL 56%

Filtered Direct Preference Optimization

Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, Kaito Ariu

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

Comments EMNLP 2024

2405.11848 2024-12-03 stat.ML cs.AI cs.LG cs.NE physics.ao-ph q-bio.NC 56%

Alternators For Sequence Modeling

Mohammad Reza Rezaei, Adji Bousso Dieng

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

Comments A new versatile family of sequence models that can be used for both generative modeling and supervised learning. The codebase will be made available upon publication. This paper is dedicated to Thomas Sankara

2411.19125 2024-12-02 cs.LG 56%

Advancing Generalization in PINNs through Latent-Space Representations

Honghui Wang, Yifan Pu, Shiji Song, Gao Huang

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

2411.12746 2024-11-21 q-fin.CP cs.AI cs.LG 56%

A Review of Reinforcement Learning in Financial Applications

Yahui Bai, Yuhe Gao, Runzhe Wan, Sheng Zhang, Rui Song

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

2411.00588 2024-11-04 cs.LG cs.AI 56%

$α$-TCVAE: On the relationship between Disentanglement and Diversity

Cristian Meo, Louis Mahon, Anirudh Goyal, Justin Dauwels

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

2402.07963 2024-11-01 cs.AI cs.LG 56%

SPO: Sequential Monte Carlo Policy Optimisation

Matthew V Macfarlane, Edan Toledo, Donal Byrne, Paul Duckworth, Alexandre Laterre

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 NeurIPS 2024. 34 pages, 3 main figures

2408.16862 2024-10-30 stat.ML cs.LG 56%

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics

Yenho Chen, Noga Mudrik, Kyle A. Johnsen, Sankaraleengam Alagapan, Adam S. Charles, Christopher J. Rozell

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

Comments Accepted to NeurIPS 2024

2306.00840 2024-10-15 cs.LG cs.AI 56%

What model does MuZero learn?

Jinke He, Thomas M. Moerland, Joery A. de Vries, Frans A. Oliehoek

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

Comments ECAI 2024

2410.01968 2024-10-04 cs.RO 56%

Bi-Level Motion Imitation for Humanoid Robots

Wenshuai Zhao, Yi Zhao, Joni Pajarinen, Michael Muehlebach

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

Comments CoRL 2024

2312.04386 2024-09-18 cs.LG cs.AI 56%

Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization

Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters

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

Comments arXiv admin note: substantial text overlap with arXiv:2302.12526

2403.04899 2024-07-22 cs.CV cs.AI 56%

Towards Scene Graph Anticipation

Rohith Peddi, Saksham Singh, Saurabh, Parag Singla, Vibhav Gogate

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

Comments ECCV 2024, Code: https://github.com/rohithpeddi/SceneSayer

2405.17784 2024-06-05 cs.LG cs.AI 56%

Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation

Ignat Georgiev, Krishnan Srinivasan, Jie Xu, Eric Heiden, Animesh Garg

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

Comments Website https://adaptive-horizon-actor-critic.github.io/

2405.18520 2024-05-30 cs.LG cs.AI 56%

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan

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

2402.08530 2024-05-27 cs.LG cs.AI stat.ML 56%

A Distributional Analogue to the Successor Representation

Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Yunhao Tang, André Barreto, Will Dabney, Marc G. Bellemare, Mark Rowland

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 ICML 2024. First two authors contributed equally

2402.00085 2024-05-21 cs.LG cs.AI 56%

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning

Xuecheng Niu, Akinori Ito, Takashi Nose

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 IEEE Access

Journal ref IEEE Access, vol. 12, pp. 46940-46952, 2024

2310.04159 2024-04-16 cs.LG 56%

Amortized Network Intervention to Steer the Excitatory Point Processes

Zitao Song, Wendi Ren, Shuang Li

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

2403.14110 2024-03-22 cs.LG cs.AI 56%

Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method

Kyuwon Choi, Cheolkyun Rho, Taeyoun Kim, Daewoo Choi

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

Comments 7 pages, 8 figures

2310.00229 2024-03-19 cs.AI cs.LG 56%

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

Mingde Zhao, Safa Alver, Harm van Seijen, Romain Laroche, Doina Precup, Yoshua Bengio

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

Comments ICLR 2024 Camera-Ready

2306.17366 2024-03-04 cs.LG cs.AI 56%

$λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models

Claas A Voelcker, Arash Ahmadian, Romina Abachi, Igor Gilitschenski, 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

2401.13282 2024-01-25 cs.LG cs.AI 56%

RefreshNet: Learning Multiscale Dynamics through Hierarchical Refreshing

Junaid Farooq, Danish Rafiq, Pantelis R. Vlachas, Mohammad Abid Bazaz

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

2401.07369 2024-01-17 cs.LG cs.RO 56%

CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design

Zeji Yi, Chaoyi Pan, Guanqi He, Guannan Qu, Guanya Shi

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

Comments 32 pages, 4 figures

2302.11048 2023-12-29 cs.LG cs.AI 56%

Adversarial Model for Offline Reinforcement Learning

Mohak Bhardwaj, Tengyang Xie, Byron Boots, Nan Jiang, Ching-An Cheng

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

Comments Accepted at the Neural Information Processing Systems (NeurIPS), 2023. Mohak Bhardwaj and Tengyang Xie contributed equally to this work. arXiv admin note: text overlap with arXiv:2211.04538

2303.10426 2023-11-30 cs.LG 56%

Discovering Predictable Latent Factors for Time Series Forecasting

Jingyi Hou, Zhen Dong, Jiayu Zhou, Zhijie Liu

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

2309.12671 2023-10-25 cs.LG cs.AI 56%

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization

Hai Zhang, Hang Yu, Junqiao Zhao, Di Zhang, Chang Huang, Hongtu Zhou, Xiao Zhang, Chen Ye

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

1. 模型式强化学习 1126 篇

Distributional Successor Features Enable Zero-Shot Policy Optimization

Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes

Diminishing Return of Value Expansion Methods

Provably Efficient Exploration in Reward Machines with Low Regret

Reinforcement Learning Ship Autopilot: Sample efficient and Model Predictive Control-based Approach

Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity

Filtered Direct Preference Optimization

Alternators For Sequence Modeling

Advancing Generalization in PINNs through Latent-Space Representations

A Review of Reinforcement Learning in Financial Applications

$α$-TCVAE: On the relationship between Disentanglement and Diversity

SPO: Sequential Monte Carlo Policy Optimisation

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics

What model does MuZero learn?

Bi-Level Motion Imitation for Humanoid Robots

Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization

Towards Scene Graph Anticipation

Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

A Distributional Analogue to the Successor Representation

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning

Amortized Network Intervention to Steer the Excitatory Point Processes

Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

$λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models

RefreshNet: Learning Multiscale Dynamics through Hierarchical Refreshing

CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design

Adversarial Model for Offline Reinforcement Learning

Discovering Predictable Latent Factors for Time Series Forecasting

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization