{"total":100,"rows":[{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74,"area":"alignment"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2310.14554","title":"Making RL with Preference-based Feedback Efficient via Randomization","created":"2023-10-23","cited_by_count":46,"area":"alignment"},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2302.11048","title":"Adversarial Model for Offline Reinforcement Learning","created":"2023-02-21","cited_by_count":31,"area":"offlinerl"},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2206.01315","title":"Sample-Efficient Reinforcement Learning of Partially Observable Markov Games","created":"2022-06-02","cited_by_count":27,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2209.14990","title":"Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms","created":"2022-09-29","cited_by_count":24,"area":null},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2402.06734","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","created":"2024-02-09","cited_by_count":20,"area":"alignment"},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"area":null},{"id":"2205.13476","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","created":"2022-05-26","cited_by_count":16,"area":null},{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14,"area":"alignment"},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"area":"deeprl"},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11,"area":"deeprl"},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2211.04538","title":"ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data","created":"2022-11-08","cited_by_count":9,"area":"offlinerl"},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2503.15200","title":"Partially Observable Reinforcement Learning with Memory Traces","created":"2025-03-19","cited_by_count":9,"area":"deeprl"},{"id":"2306.12356","title":"Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2407.07333","title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy","created":"2024-07-10","cited_by_count":7,"area":"deeprl"},{"id":"2209.14997","title":"Optimistic MLE -- A Generic Model-based Algorithm for Partially Observable Sequential Decision Making","created":"2022-09-29","cited_by_count":6,"area":null},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2406.02295","title":"How to Explore with Belief: State Entropy Maximization in POMDPs","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2409.16824","title":"Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability","created":"2024-09-25","cited_by_count":5,"area":"deeprl"},{"id":"2307.02884","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2310.07596","title":"Prospective Side Information for Latent MDPs","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2408.06542","title":"Value of Information and Reward Specification in Active Inference and POMDPs","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2501.13312","title":"Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2510.06540","title":"Scalable Policy-Based RL Algorithms for POMDPs","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2402.18159","title":"Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation","created":"2024-02-28","cited_by_count":3,"area":"deeprl"},{"id":"2406.07920","title":"Near-Optimal Learning and Planning in Separated Latent MDPs","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2502.02331","title":"On the Impact of Performative Risk Minimization for Binary Random Variables","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2505.17801","title":"Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour","created":"2025-05-23","cited_by_count":3,"area":"agents"},{"id":"2510.03207","title":"To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning","created":"2025-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2404.14552","title":"Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs","created":"2024-04-22","cited_by_count":2,"area":"deeprl"},{"id":"2507.09742","title":"Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2310.06243","title":"Sample-Efficient Multi-Agent RL: An Optimization Perspective","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2402.03282","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","created":"2024-02-05","cited_by_count":1,"area":"alignment"},{"id":"2407.15820","title":"On shallow planning under partial observability","created":"2024-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2410.01331","title":"Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2503.00206","title":"Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach","created":"2025-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2505.16547","title":"Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulation","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.01919","title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2508.02103","title":"Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation","created":"2025-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2510.14315","title":"Active Measuring in Reinforcement Learning With Delayed Negative Effects","created":"2025-10-16","cited_by_count":1,"area":"deeprl"},{"id":"2601.18930","title":"Toward Learning POMDPs Beyond Full-Rank Actions and State Observability","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2605.06377","title":"Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.31261","title":"Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2306.08762","title":"Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2310.10107","title":"Posterior Sampling-based Online Learning for Episodic POMDPs","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2312.00727","title":"Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2402.18149","title":"Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation","created":"2024-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2412.21001","title":"LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency","created":"2024-12-30","cited_by_count":0,"area":"alignment"},{"id":"2501.18790","title":"Achieving $\\widetilde{\\mathcal{O}}(\\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2504.16115","title":"A Framework for Objective-Driven Dynamical Stochastic Fields","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.18883","title":"Success in Humanoid Reinforcement Learning under Partial Observation","created":"2025-07-25","cited_by_count":0,"area":"deeprl"},{"id":"2509.06490","title":"MORSE: Multi-Objective Reinforcement Learning via Strategy Evolution for Supply Chain Optimization","created":"2025-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2601.20764","title":"Agentic Fog: A Policy-driven Framework for Distributed Intelligence in Fog Computing","created":"2026-01-28","cited_by_count":0,"area":"agents"},{"id":"2603.03480","title":"Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2603.27389","title":"Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning","created":"2026-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2606.02363","title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.18393","title":"Learning-Based Decision Making for Combustion Phasing Control in Multi-Fuel CI Engines with Latent Fuel Reactivity Estimation","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2608.02433","title":"Foundations of Reinforcement Learning and Control:Connections and New Perspectives","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"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":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}