{"total":94,"rows":[{"id":"2306.10374","title":"A Survey of Contextual Optimization Methods for Decision Making under Uncertainty","created":"2023-06-17","cited_by_count":82,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"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":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","cited_by_count":49,"area":null},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32,"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":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"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":"2302.01244","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2201.00248","title":"Transfer RL across Observation Feature Spaces via Model-Based Regularization","created":"2022-01-01","cited_by_count":18,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","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":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12,"area":"wm"},{"id":"2406.04219","title":"Multi-Agent Imitation Learning: Value is Easy, Regret is Hard","created":"2024-06-06","cited_by_count":11,"area":"offlinerl"},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2606.15032","title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","created":"2026-06-13","cited_by_count":10,"area":"wm"},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2307.01708","title":"Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning","created":"2023-07-04","cited_by_count":9,"area":null},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9,"area":"offlinerl"},{"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":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8,"area":"offlinerl"},{"id":"2211.13937","title":"Operator Splitting Value Iteration","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2402.12874","title":"Skill or Luck? Return Decomposition via Advantage Functions","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"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":"2605.30880","title":"PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments","created":"2026-05-29","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":"2206.03674","title":"Integrating Symmetry into Differentiable Planning with Steerable Convolutions","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2210.13542","title":"Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation","created":"2022-10-24","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":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"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":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2406.15850","title":"Learning Abstract World Model for Value-preserving Planning with Options","created":"2024-06-22","cited_by_count":4,"area":"wm"},{"id":"2605.15960","title":"Imperfect World Models are Exploitable","created":"2026-05-15","cited_by_count":4,"area":"wm"},{"id":"2306.11208","title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2602.05999","title":"On the Role of Computation in Reinforcement Learning","created":"2026-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2605.01694","title":"Latent State Design for World Models under Sufficiency Constraints","created":"2026-05-03","cited_by_count":3,"area":"wm"},{"id":"2608.12939","title":"Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency","created":"2026-08-13","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":"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":"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":"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":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2404.19292","title":"Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2505.13709","title":"Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning","created":"2025-05-19","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":"2511.05849","title":"EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph","created":"2025-11-08","cited_by_count":2,"area":null},{"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":"2105.04129","title":"Parameter-free Gradient Temporal Difference Learning","created":"2021-05-10","cited_by_count":1,"area":null},{"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":"2304.03365","title":"Decision-Focused Model-based Reinforcement Learning for Reward Transfer","created":"2023-04-06","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":"2406.16006","title":"Bounding-Box Inference for Error-Aware Model-Based Reinforcement Learning","created":"2024-06-23","cited_by_count":1,"area":"deeprl"},{"id":"2510.17709","title":"Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimality","created":"2025-10-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2608.04896","title":"When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.02322","title":"What Is Worth Representing? Representational Empowerment for Continual Model Construction","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2310.07706","title":"Pixel State Value Network for Combined Prediction and Planning in Interactive Environments","created":"2023-10-11","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":"2603.27751","title":"SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games","created":"2026-03-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.25357","title":"Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.25923","title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.06640","title":"What a World Model Represents Is Three Questions","created":"2026-07-07","cited_by_count":0,"area":"wm"},{"id":"2608.19779","title":"An Irreducible Quantum Advantage in Aligning World Models with Reality","created":"2026-08-20","cited_by_count":0,"area":"wm"},{"id":"2609.05834","title":"Learning Counterfactual World Models for Embodied Reasoning under Partial Observability","created":"2026-09-05","cited_by_count":0,"area":"wm"},{"id":"2609.09597","title":"Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints","created":"2026-09-09","cited_by_count":0,"area":"wm"},{"id":"2609.18950","title":"Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL","created":"2026-07-15","cited_by_count":0,"area":"wm"},{"id":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33030","title":"What Must a World Model Distinguish for Planning?","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.38334","title":"EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2610.00921","title":"In CEM, a World Model Is Also a Proposal Mechanism","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.04494","title":"DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents","created":"2026-10-03","cited_by_count":0,"area":"wm"},{"id":"2610.05550","title":"When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models","created":"2026-10-04","cited_by_count":0,"area":"wm"},{"id":"2610.11942","title":"Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.14368","title":"History, Adaptation, and Hidden Gain: Two Prospective Tests of Learned Predictive Control in a Synthetic Neural Population","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14413","title":"Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16763","title":"Relational Learning as World Modeling","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.19375","title":"One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}