Model-Based RL

ICLR 2024arXiv:2310.06114

#2

Learning Interactive Real-World Simulators

Sherry Yang, Yilun Du, Seyed Ghasemipour et al.

350

ICML 2024arXiv:2312.11456

#3

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Wei Xiong, Hanze Dong, Chenlu Ye et al.

reinforcement learning from human feedbackreverse-kl regularizationcontextual bandit formulationdirect preference optimization+4

312

ICLR 2024arXiv:2310.16828

#4

TD-MPC2: Scalable, Robust World Models for Continuous Control

Nicklas Hansen, Hao Su, Xiaolong Wang

308

ECCV 2024arXiv:2309.09777

#5

DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

Xiaofeng Wang, Zheng Zhu, Guan Huang et al.

world modelsautonomous drivingdiffusion modelsdriving video generation+3

239

NEURIPS 2025arXiv:2504.20571

#6

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Yiping Wang, Qing Yang, Zhiyuan Zeng et al.

190

NEURIPS 2025arXiv:2504.13958

#7

ToolRL: Reward is All Tool Learning Needs

Cheng Qian, Emre Can Acikgoz, Qi He et al.

178

ECCV 2024arXiv:2311.16038

#8

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

Wenzhao Zheng, Weiliang Chen, Yuanhui Huang et al.

172

ICLR 2024arXiv:2310.12921

#9

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Juan Rocamonde, Victoriano Montesinos, Elvis Nava et al.

137

NEURIPS 2025arXiv:2504.16084

#10

TTRL: Test-Time Reinforcement Learning

Yuxin Zuo, Kaiyan Zhang, Li Sheng et al.

test-time reinforcement learningreward estimationlarge language modelsreasoning tasks+4

129

ICML 2025arXiv:2411.04983

#11

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Gaoyue Zhou, Hengkai Pan, Yann LeCun et al.

126

ICLR 2025arXiv:1901.03559

#12

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Thomas Bush, Stephen Chung, Usman Anwar et al.

model-free reinforcement learningconcept-based interpretabilityemergent planningmechanistic interpretability+3

125

ICLR 2025arXiv:2411.02337

#13

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Zehan Qi, Xiao Liu, Iat Long Iong et al.

llm web agentsonline curriculum reinforcement learningself-evolving curriculumoutcome-supervised reward model+3

121

ICML 2024arXiv:2402.03681

#14

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback

Yufei Wang, Zhanyi Sun, Jesse Zhang et al.

reward engineeringvision language modelspreference learningautonomous manipulation+4

119

ICML 2024arXiv:2404.12377

#15

RoboDreamer: Learning Compositional World Models for Robot Imagination

Siyuan Zhou, Yilun Du, Jiaben Chen et al.

text-to-video modelscompositional world modelsrobot decision-makingvideo generation+2

107

NEURIPS 2025arXiv:2505.24864

#16

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Mingjie Liu, Shizhe Diao, Ximing Lu et al.

reinforcement learningreasoning capabilitieskl divergence controlreference policy resetting+4

104

ICLR 2024arXiv:2311.01017

#17

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Lunjun Zhang, Yuwen Xiong, Ze Yang et al.

94

COLM 2025arXiv:2504.07912

#18

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Rosie Zhao, Alexandru Meterez, Sham M. Kakade et al.

reinforcement learninglanguage modelspost-trainingppo+2

87

ICLR 2024arXiv:2405.01534

#19

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

Murtaza Dalal, Tarun Chiruvolu, Devendra Chaplot et al.

76

ICLR 2024arXiv:2310.08887

#20

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Seohong Park, Oleh Rybkin, Sergey Levine

75

ICLR 2024arXiv:2310.04373

#21

Confronting Reward Model Overoptimization with Constrained RLHF

Ted Moskovitz, Aaditya Singh, DJ Strouse et al.

75

ICLR 2025arXiv:2502.05485

#22

HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation

Yi Li, Yuquan Deng, Jesse Zhang et al.

75

ICML 2024arXiv:2308.01399

#23

Learning to Model the World With Language

Jessy Lin, Yuqing Du, Olivia Watkins et al.

world modelslanguage groundingmultimodal predictionself-supervised learning+4

71

ICLR 2025arXiv:2410.13232

#24

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Hyungjoo Chae, Namyoung Kim, Kai Ong et al.

web navigation agentsworld modelslarge language modelsautonomous agents+4

65

NEURIPS 2025arXiv:2504.07954

#25

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

En Yu, Kangheng Lin, Liang Zhao et al.

62

ICML 2024arXiv:2402.15567

#26

Foundation Policies with Hilbert Representations

Seohong Park, Tobias Kreiman, Sergey Levine

unsupervised pre-trainingreinforcement learning policiesoffline datazero-shot adaptation+4

59

ICML 2024arXiv:2402.05808

#27

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Zhiheng Xi, Wenxiang Chen, Boyang Hong et al.

reinforcement learninglarge language modelsreasoning tasksoutcome supervision+4

58

ICCV 2025arXiv:2504.20995

#28

Learning 4D Embodied World Models

Haoyu Zhen, Qiao Sun, Hongxin Zhang et al.

4d world modelsembodied agent actionsrgb-dn video generationinverse dynamic models+4

45

NEURIPS 2025arXiv:2506.05284

#29

Video World Models with Long-term Spatial Memory

Tong Wu, Shuai Yang, Ryan Po et al.

video world modelslong-term spatial memoryscene consistencyautoregressive video generation+3

44

ICML 2025arXiv:2503.18938

#30

AdaWorld: Learning Adaptable World Models with Latent Actions

Shenyuan Gao, Siyuan Zhou, Yilun Du et al.

44

ICLR 2024arXiv:2401.08898

#31

Bridging State and History Representations: Understanding Self-Predictive RL

Tianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi et al.

44

AAAI 2025arXiv:2408.14197

#32

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving

Yu Yang, Jianbiao Mei, Yukai Ma et al.

43

reinforcement learningautonomous drivingworld modellatent state space+4

#33

Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-v2)

Qifeng Li, Xiaosong Jia, Shaobo Wang et al.

ECCV 2024

43

ICLR 2024arXiv:2311.11385

#34

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

Ahmed Hendawy, Jan Peters, Carlo D'Eramo

41

ICLR 2024arXiv:2302.08560

#35

Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

Harshit Sikchi, Qinqing Zheng, Amy Zhang et al.

41

ICLR 2024arXiv:2403.04253

#36

Mastering Memory Tasks with World Models

Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran et al.

40

NEURIPS 2025arXiv:2502.20694

#37

WorldModelBench: Judging Video Generation Models As World Models

Dacheng Li, Yunhao Fang, Yukang Chen et al.

video generation modelsworld modeling capabilitiesphysics adherenceinstruction-following evaluation+4

37

ICLR 2024arXiv:2307.07176

#38

SafeDreamer: Safe Reinforcement Learning with World Models

Weidong Huang, Jiaming Ji, Chunhe Xia et al.

safe reinforcement learningworld model planninglagrangian-based methodsvision-only tasks+1

37

ICLR 2025arXiv:2406.08407

#39

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Xuehai He, Weixi Feng, Kaizhi Zheng et al.

multimodal video understandingworld model evaluationmultimodal language modelscounterfactual reasoning+3

36

ICLR 2025arXiv:2504.11054

#40

Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models

Andrea Tirinzoni, Ahmed Touati, Jesse Farebrother et al.

34

CVPR 2025arXiv:2501.09781

#41

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Zhongwei Ren, Yunchao Wei, Xun Guo et al.

33

ICLR 2024arXiv:2305.18246

#42

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

Haque Ishfaq, Qingfeng Lan, Pan Xu et al.

33

ICLR 2024arXiv:2404.12308

#43

ASID: Active Exploration for System Identification in Robotic Manipulation

Marius Memmel, Andrew Wagenmaker, Chuning Zhu et al.

29

ICML 2024arXiv:2402.08848

#44

Hybrid Inverse Reinforcement Learning

Juntao Ren, Gokul Swamy, Steven Wu et al.

inverse reinforcement learningimitation learninghybrid reinforcement learningexpert-competitive rl+4

29

ICML 2024arXiv:2312.12275

#45

Emergence of In-Context Reinforcement Learning from Noise Distillation

Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin et al.

in-context reinforcement learningnoise-induced curriculumdata acquisitionsynthetic noise injection+2

26

ICML 2024arXiv:2405.08740

#46

Reinformer: Max-Return Sequence Modeling for Offline RL

Zifeng Zhuang, Dengyun Peng, Jinxin Liu et al.

offline reinforcement learningsequence modelingtrajectory stitchingreturn maximization+3

25

ECCV 2024arXiv:2409.18343

#47

Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving

Zhenghao Peng, Wenjie Luo, Yiren Lu et al.

autonomous drivingagent behavior modelingreinforcement learning fine-tuningdistribution shift+4

25

ICLR 2025arXiv:2412.14957

#48

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro et al.

25

ICLR 2025arXiv:2407.07086

#49

Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

Logan Cross, Violet Xiang, Agam Bhatia et al.

multi-agent reinforcement learningtheory of mindlarge language modelshierarchical planning+4

ICLR 2025arXiv:2412.12098

#50

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

Bhavya, Stelian Coros, Andreas Krause et al.

ICML 2024arXiv:2405.17784

#51

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

Ignat Georgiev, Krishnan Srinivasan, Jie Xu et al.

policy gradient theoremdifferentiable simulationcontact-rich simulationfirst-order model-based rl+4

ICLR 2025arXiv:2501.16142

#52

Towards General-Purpose Model-Free Reinforcement Learning

Scott Fujimoto, Pierluca D'Oro, Amy Zhang et al.

model-free reinforcement learningmodel-based representationsvalue function linearizationgeneral-purpose rl+2

ICLR 2025arXiv:2405.18418

#53

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

Nick Hansen, Jyothir S V, Vlad Sobal et al.

whole-body controlhumanoid roboticsvisual observationshierarchical world model+4

23

ICLR 2024arXiv:2307.13372

#54

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

Haoqi Yuan, Zhancun Mu, Feiyang Xie et al.

Targeted Representation Alignment for Open-World Semi-Supervised Learning

Ruixuan Xiao, Lei Feng, Kai Tang et al.

Submodular Reinforcement Learning

Manish Prajapat, Mojmir Mutny, Melanie Zeilinger et al.

22

ICLR 2025arXiv:2410.07927

#57

Efficient Reinforcement Learning with Large Language Model Priors

Xue Yan, Yan Song, Xidong Feng et al.

reinforcement learninglarge language modelssequential decision-makingbayesian inference+3

21

NEURIPS 2025arXiv:2505.16394

#58

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

Zhenjie Yang, Xiaosong Jia, Qifeng Li et al.

reinforcement learningautonomous drivingworld modelsmodel-based reinforcement learning+4

21

NEURIPS 2025arXiv:2505.11711

#59

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

Sagnik Mukherjee, Lifan Yuan, Dilek Hakkani-Tur et al.

20

NEURIPS 2025arXiv:2505.13934

#60

RLVR-World: Training World Models with Reinforcement Learning

Jialong Wu, Shaofeng Yin, Ningya Feng et al.

19

ICML 2024arXiv:2406.19320

#61

Efficient World Models with Context-Aware Tokenization

Vincent Micheli, Eloi Alonso, François Fleuret

world modelsreinforcement learningsequence modelingdiscrete autoencoder+4

ICML 2025arXiv:2411.04434

#62

Scaling Laws for Pre-training Agents and World Models

Tim Pearce, Tabish Rashid, David Bignell et al.

NEURIPS 2025arXiv:2506.23135

#63

RoboScape: Physics-informed Embodied World Model

Yu Shang, Xin Zhang, Yinzhou Tang et al.

embodied world modelsphysics-informed learningvideo generationtemporal depth prediction+4

ICML 2024arXiv:2310.00344

#64

HarmonyDream: Task Harmonization Inside World Models

Haoyu Ma, Jialong Wu, Ningya Feng et al.

model-based reinforcement learningworld model learningobservation modelingreward modeling+4

ICLR 2024arXiv:2405.11778

#65

Efficient Multi-agent Reinforcement Learning by Planning

Qihan Liu, Jianing Ye, Xiaoteng Ma et al.

NEURIPS 2025arXiv:2506.09981

#66

ReSim: Reliable World Simulation for Autonomous Driving

Jiazhi Yang, Kashyap Chitta, Shenyuan Gao et al.

autonomous driving simulationworld modelsdiffusion transformer architecturedriving scenario generation+3

ICLR 2024arXiv:2310.07220

#67

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Xiyao Wang, Ruijie Zheng, Yanchao Sun et al.

ICLR 2024arXiv:2401.13034

#68

Locality Sensitive Sparse Encoding for Learning World Models Online

Zichen Liu, Chao Du, Wee Sun Lee et al.

model-based reinforcement learningonline learningcatastrophic forgettinglocality sensitive hashing+4

NEURIPS 2025arXiv:2505.05495

#69

Learning 3D Persistent Embodied World Models

Siyuan Zhou, Yilun Du, Yuncong Yang et al.

video diffusion models3d spatial mappingembodied world modelslong-horizon simulation+4

17

ICML 2024arXiv:2404.18909

#70

Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty

Laixi Shi, Eric Mazumdar, Yuejie Chi et al.

multi-agent reinforcement learningdistributionally robust markov gamesrobust equilibrium strategiesgame-theoretic equilibria+4

17

ICLR 2025arXiv:2310.20025

#71

GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models

Mianchu Wang, Rui Yang, Xi Chen et al.

offline reinforcement learninggoal-conditioned rlmodel-based planningmulti-modal action distribution+4

16

ICLR 2024arXiv:2403.10760

#72

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

Yoonyoung Cho, Junhyek Han, Yoontae Cho et al.

16

AAAI 2024arXiv:2310.02456

#73

Learning Optimal Advantage from Preferences and Mistaking It for Reward

W Bradley Knox, Stephane Hatgis-Kessell, Sigurdur Orn Adalgeirsson et al.

reward function learninghuman preference modelingregret preference modelpartial return assumption+4

16

NEURIPS 2025arXiv:2505.11792

#74

Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling

Yitian Chen, Jingfan Xia, Siyu Shao et al.

optimization modelinglarge language modelsreinforcement learningsolver verification+4

ECCV 2024arXiv:2303.10571

#75

Reinforcement Learning Friendly Vision-Language Model for Minecraft

Haobin Jiang, Junpeng Yue, Hao Luo et al.

vision-language modelreinforcement learning friendlycontrastive learning frameworkintrinsic reward function+4

ICLR 2025arXiv:2410.09486

#76

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

Yarden As, Bhavya, Lenart Treven et al.

reinforcement learningsafe explorationmodel-based rlprobabilistic dynamics model+3

ICLR 2024arXiv:2310.06089

#77

Predictive auxiliary objectives in deep RL mimic learning in the brain

Ching Fang, Kimberly Stachenfeld

ICLR 2025arXiv:2410.04631

#78

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL

Mathias Jackermeier, Alessandro Abate

ICLR 2025arXiv:2502.12130

#79

Scaling Autonomous Agents via Automatic Reward Modeling And Planning

Zhenfang Chen, Delin Chen, Rui Sun et al.

automatic reward modelingmulti-step decision-makingllm-based agentstask planning+3

AAAI 2024arXiv:2312.09539

#80

Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning

Xiao Du, Yutong Ye, Pengyu Zhang et al.

ICML 2025arXiv:2502.15280

#81

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

Hojoon Lee, Youngdo Lee, Takuma Seno et al.

ICLR 2024arXiv:2403.09859

#82

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

Zohar Rimon, Tom Jurgenson, Orr Krupnik et al.

ICLR 2025arXiv:2501.13072

#83

AdaWM: Adaptive World Model based Planning for Autonomous Driving

Hang Wang, Xin Ye, Feng Tao et al.

world model reinforcement learningautonomous driving planningdistribution shiftdynamics model mismatch+4

ECCV 2024arXiv:2407.15626

#84

Reinforcement Learning Meets Visual Odometry

Nico Messikommer, Giovanni Cioffi, Mathias Gehrig et al.

visual odometryreinforcement learningkeyframe selectionsequential decision-making+4

CVPR 2024arXiv:2312.09056

#85

ReCoRe: Regularized Contrastive Representation Learning of World Model

Rudra P, K. Poudel, Harit Pandya et al.

contrastive representation learningworld modelreinforcement learningvisual navigation+4

volumetric representationsautonomous drivingmotion planningneural volumetric world modeling+4

#86

Neural Volumetric World Models for Autonomous Driving

Zanming Huang, Jimuyang Zhang, Eshed Ohn-Bar

ECCV 2024

ICLR 2024arXiv:2305.18505

#87

Provable Reward-Agnostic Preference-Based Reinforcement Learning

Wenhao Zhan, Masatoshi Uehara, Wen Sun et al.

NEURIPS 2025arXiv:2505.11289

#88

Meta-World+: An Improved, Standardized, RL Benchmark

Reginald McLean, Evangelos Chatzaroulas, Luc McCutcheon et al.

ICLR 2024arXiv:2306.03346

#89

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data

Chongyi Zheng, Benjamin Eysenbach, Homer Walke et al.

ICLR 2024arXiv:2306.09205

#90

Reward-Free Curricula for Training Robust World Models

Marc Rigter, Minqi Jiang, Ingmar Posner

ICLR 2025arXiv:2503.04416

#91

Learning Transformer-based World Models with Contrastive Predictive Coding

Maxime Burchi, Radu Timofte

transformer-based world modelscontrastive predictive codingmodel-based reinforcement learningnext state prediction+2

ICCV 2025arXiv:2508.17600

#92

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

Guanxing Lu, Baoxiong Jia, Puhao Li et al.

CVPR 2025arXiv:2410.17856

#93

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

Shaofei Cai, Zihao Wang, Kewei Lian et al.

ICML 2024arXiv:2402.05643

#94

Improving Token-Based World Models with Parallel Observation Prediction

Lior Cohen, Kaixin Wang, Bingyi Kang et al.

token-based world modelsparallel observation predictionretentive networksreinforcement learning+4

NEURIPS 2025arXiv:2510.16907

#95

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

Kangrui Wang, Pingyue Zhang, Zihan Wang et al.

NEURIPS 2025arXiv:2506.12811

#96

Flow-Based Policy for Online Reinforcement Learning

Lei Lv, Yunfei Li, Yu Luo et al.

flow-based policyonline reinforcement learningwasserstein-2 regularizationmultimodal action distributions+3

ICLR 2024arXiv:2307.12062

#97

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Yongyuan Liang, Yanchao Sun, Ruijie Zheng et al.

ICML 2024arXiv:2405.06263

#98

Learning Latent Dynamic Robust Representations for World Models

Ruixiang Sun, Hongyu Zang, Xin Li et al.

model-based reinforcement learningworld modelsspatio-temporal maskingbisimulation principle+4

ICLR 2025arXiv:2410.11689

#99

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami et al.

11

ICLR 2024arXiv:2307.06175

#100

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

Kai Cui, Sascha Hauck, Christian Fabian et al.

11