{"total":527,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302,"area":"offlinerl"},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2203.09168","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","created":"2022-03-17","cited_by_count":120,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2102.08501","title":"DEUP: Direct Epistemic Uncertainty Prediction","created":"2021-02-16","cited_by_count":104,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2102.11409","title":"On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty","created":"2021-02-22","cited_by_count":87,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2308.05384","title":"Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization","created":"2023-08-10","cited_by_count":56,"area":"diffusion"},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2402.16359","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","created":"2024-02-26","cited_by_count":53,"area":"diffusion"},{"id":"2310.17918","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","created":"2023-10-27","cited_by_count":51,"area":null},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2105.11982","title":"Quantifying Uncertainty in Deep Spatiotemporal Forecasting","created":"2021-05-25","cited_by_count":48,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44,"area":"deeprl"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2203.03048","title":"Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors","created":"2022-03-06","cited_by_count":39,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2212.09184","title":"Faithful Heteroscedastic Regression with Neural Networks","created":"2022-12-18","cited_by_count":37,"area":null},{"id":"2306.05724","title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","created":"2023-06-09","cited_by_count":36,"area":null},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2308.05021","title":"On Error Propagation of Diffusion Models","created":"2023-08-09","cited_by_count":31,"area":"diffusion"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2402.04080","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","created":"2024-02-06","cited_by_count":31,"area":"diffusion"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2509.09675","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","created":"2025-09-11","cited_by_count":29,"area":"lr"},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2102.04399","title":"How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation","created":"2021-02-08","cited_by_count":27,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2202.07152","title":"L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2310.02823","title":"Learning to Scale Logits for Temperature-Conditional GFlowNets","created":"2023-10-04","cited_by_count":27,"area":null},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2107.04271","title":"FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning","created":"2021-07-09","cited_by_count":26,"area":null},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2305.20065","title":"Latent Exploration for Reinforcement Learning","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2311.06234","title":"EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy","created":"2023-11-10","cited_by_count":21,"area":null},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20,"area":"offlinerl"},{"id":"2004.10398","title":"Sequential Anomaly Detection using Inverse Reinforcement Learning","created":"2020-04-22","cited_by_count":20,"area":"offlinerl"},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"area":null}],"next_cursor":"100"}