{"total":93,"rows":[{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392,"area":"agents"},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"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":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2202.03813","title":"Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters","created":"2022-02-08","cited_by_count":22,"area":null},{"id":"1801.06176","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","created":"2018-01-18","cited_by_count":21,"area":"wm"},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2503.04416","title":"Learning Transformer-based World Models with Contrastive Predictive Coding","created":"2025-03-06","cited_by_count":20,"area":"wm"},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2405.15083","title":"MuDreamer: Learning Predictive World Models without Reconstruction","created":"2024-05-23","cited_by_count":13,"area":"wm"},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2109.04261","title":"Learning cortical representations through perturbed and adversarial dreaming","created":"2021-09-09","cited_by_count":10,"area":null},{"id":"2201.09765","title":"Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning","created":"2022-01-24","cited_by_count":10,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2211.13937","title":"Operator Splitting Value Iteration","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"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":"2509.09737","title":"World Modeling with Probabilistic Structure Integration","created":"2025-09-10","cited_by_count":7,"area":"wm"},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"1801.09624","title":"Learning the Reward Function for a Misspecified Model","created":"2018-01-29","cited_by_count":4,"area":"alignment"},{"id":"2102.12194","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2305.14223","title":"Co-Learning Empirical Games and World Models","created":"2023-05-23","cited_by_count":4,"area":"wm"},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2606.01626","title":"IMWM: Intuition Models Complement World Models for Latent Planning","created":"2026-06-01","cited_by_count":4,"area":"wm"},{"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":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2402.04567","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","created":"2024-02-07","cited_by_count":3,"area":"offlinerl"},{"id":"2406.08404","title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2506.02612","title":"Simple, Good, Fast: Self-Supervised World Models Free of Baggage","created":"2025-06-03","cited_by_count":3,"area":"wm"},{"id":"2602.05999","title":"On the Role of Computation in Reinforcement Learning","created":"2026-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2604.06155","title":"Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement","created":"2026-04-07","cited_by_count":3,"area":"wm"},{"id":"2608.29998","title":"The Intervention Gap in Latent World Models","created":"2026-08-30","cited_by_count":3,"area":"wm"},{"id":"2202.01461","title":"ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2205.08712","title":"CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks","created":"2022-05-18","cited_by_count":2,"area":"driving"},{"id":"2205.10736","title":"Should Models Be Accurate?","created":"2022-05-22","cited_by_count":2,"area":null},{"id":"2206.02025","title":"Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning","created":"2022-06-04","cited_by_count":2,"area":null},{"id":"2210.14361","title":"Auxiliary task discovery through generate-and-test","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2301.10119","title":"Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2302.04250","title":"Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2305.14644","title":"KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks","created":"2023-05-24","cited_by_count":2,"area":"wm"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.08149","title":"Ego-centric Learning of Communicative World Models for Autonomous Driving","created":"2025-06-09","cited_by_count":2,"area":"wm"},{"id":"2607.04464","title":"Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models","created":"2026-07-05","cited_by_count":2,"area":"wm"},{"id":"2608.22092","title":"Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does","created":"2026-08-22","cited_by_count":2,"area":null},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2106.05535","title":"Differentiable Robust LQR Layers","created":"2021-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2210.00828","title":"Mastering Spatial Graph Prediction of Road Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2310.05672","title":"Multi-timestep models for Model-based Reinforcement Learning","created":"2023-10-09","cited_by_count":1,"area":"offlinerl"},{"id":"2401.11660","title":"Differentiable Tree Search Network","created":"2024-01-22","cited_by_count":1,"area":"wm"},{"id":"2505.10992","title":"ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"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":"2608.26190","title":"Predicting Consequences and Reinforcing Navigation Policies with Latent World Models","created":"2026-08-23","cited_by_count":1,"area":"wm"},{"id":"2111.09908","title":"Visual Goal-Directed Meta-Learning with Contextual Planning Networks","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2210.04820","title":"Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2211.03281","title":"Reward-Predictive Clustering","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2212.07123","title":"Reinforcement Learning in System Identification","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2312.05759","title":"Beyond One Model Fits All: Ensemble Deep Learning for Autonomous Vehicles","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2406.01562","title":"A New View on Planning in Online Reinforcement Learning","created":"2024-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2406.08687","title":"AlphaZeroES: Direct score maximization outperforms planning loss minimization","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2406.19561","title":"Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning","created":"2024-06-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.33030","title":"What Must a World Model Distinguish for Planning?","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.34488","title":"FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37432","title":"Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.17391","title":"Learning to Play: Reinforcement Learning and Games","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}