{"total":57,"rows":[{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73,"area":"diffusion"},{"id":"2205.03195","title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","created":"2022-05-06","cited_by_count":61,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2105.14074","title":"Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning","created":"2021-05-28","cited_by_count":43,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2202.00728","title":"Physical Design using Differentiable Learned Simulators","created":"2022-02-01","cited_by_count":37,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27,"area":null},{"id":"2108.11204","title":"Subgoal Search For Complex Reasoning Tasks","created":"2021-08-25","cited_by_count":21,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2310.00311","title":"Efficient Planning with Latent Diffusion","created":"2023-09-30","cited_by_count":12,"area":"diffusion"},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2411.08794","title":"LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed","created":"2024-11-13","cited_by_count":10,"area":"wm"},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"id":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8,"area":"offlinerl"},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2310.06089","title":"Predictive auxiliary objectives in deep RL mimic learning in the brain","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2302.03939","title":"Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving","created":"2023-02-08","cited_by_count":6,"area":"driving"},{"id":"2406.01361","title":"Learning to Play Atari in a World of Tokens","created":"2024-06-03","cited_by_count":6,"area":"wm"},{"id":"2504.06048","title":"Trust-Region Twisted Policy Improvement","created":"2025-04-08","cited_by_count":6,"area":"deeprl"},{"id":"2110.13621","title":"Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-level","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2206.08442","title":"A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2211.11027","title":"Safe Reinforcement Learning using Data-Driven Predictive Control","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2210.01426","title":"Continuous Monte Carlo Graph Search","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2401.06005","title":"How does the primate brain combine generative and discriminative computations in vision?","created":"2024-01-11","cited_by_count":4,"area":null},{"id":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2606.01626","title":"IMWM: Intuition Models Complement World Models for Latent Planning","created":"2026-06-01","cited_by_count":4,"area":"wm"},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2208.11535","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2301.10289","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","created":"2023-01-24","cited_by_count":3,"area":null},{"id":"2302.04798","title":"Equivariant MuZero","created":"2023-02-09","cited_by_count":3,"area":"wm"},{"id":"2304.13138","title":"The Update-Equivalence Framework for Decision-Time Planning","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2503.20102","title":"Extendable Planning via Multiscale Diffusion","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2508.06096","title":"Bounding Distributional Shifts in World Modeling through Novelty Detection","created":"2025-08-08","cited_by_count":2,"area":"wm"},{"id":"2605.04525","title":"HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks","created":"2026-05-06","cited_by_count":2,"area":"diffusion"},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2105.11702","title":"Transfer Learning and Curriculum Learning in Sokoban","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2109.05022","title":"Potential-based Reward Shaping in Sokoban","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2112.05218","title":"Learning Generalizable Behavior via Visual Rewrite Rules","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2112.15521","title":"Inferring perceptual decision making parameters from behavior in production and reproduction tasks","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2411.04580","title":"Demystifying MuZero Planning: Interpreting the Learned Model","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2602.18857","title":"VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning","created":"2026-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2605.04568","title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.02777","title":"Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}