{"total":82,"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":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2203.12742","title":"Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders","created":"2022-03-23","cited_by_count":102,"area":null},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","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":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"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":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","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":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"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":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2111.05440","title":"Dealing with the Unknown: Pessimistic Offline Reinforcement Learning","created":"2021-11-09","cited_by_count":19,"area":"offlinerl"},{"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":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2006.13189","title":"Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation","created":"2020-06-23","cited_by_count":14,"area":"offlinerl"},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2107.07046","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","created":"2021-07-10","cited_by_count":12,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2211.04878","title":"Foundation Models for Semantic Novelty in Reinforcement Learning","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2408.08706","title":"Efficient Multi-Policy Evaluation for Reinforcement Learning","created":"2024-08-16","cited_by_count":9,"area":"deeprl"},{"id":"2305.11455","title":"Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models","created":"2023-05-19","cited_by_count":8,"area":"agents"},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2201.08300","title":"From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2206.07536","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2209.13126","title":"Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2303.02378","title":"Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control","created":"2023-03-04","cited_by_count":5,"area":null},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2402.03055","title":"Deep Exploration with PAC-Bayes","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2503.11339","title":"Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model","created":"2025-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2203.02298","title":"Intrinsically-Motivated Reinforcement Learning: A Brief Introduction","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2305.00127","title":"Optimal Scheduling in IoT-Driven Smart Isolated Microgrids Based on Deep Reinforcement Learning","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2307.05330","title":"The Value of Chess Squares","created":"2023-07-08","cited_by_count":2,"area":null},{"id":"2404.00940","title":"Sequential Decision-Making under Uncertainty: A Robust MDPs review","created":"2024-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2406.04088","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning","created":"2024-06-06","cited_by_count":2,"area":"offlinerl"},{"id":"2408.07712","title":"Introduction to Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2410.13463","title":"Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach","created":"2024-10-17","cited_by_count":1,"area":"deeprl"},{"id":"2412.20824","title":"Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2502.16328","title":"Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning","created":"2025-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2602.12375","title":"Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2206.01663","title":"Joint Energy Dispatch and Unit Commitment in Microgrids Based on Deep Reinforcement Learning","created":"2022-06-03","cited_by_count":0,"area":null},{"id":"2206.05200","title":"Dynamic mean field programming","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2308.01759","title":"Bag of Policies for Distributional Deep Exploration","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2308.13135","title":"Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2403.17542","title":"VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts","created":"2024-03-26","cited_by_count":0,"area":"deeprl"},{"id":"2406.14876","title":"Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2508.21488","title":"Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2511.03595","title":"Tensor-Efficient High-Dimensional Q-learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.16030","title":"Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2609.20098","title":"CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning","created":"2026-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.35525","title":"Deep Epistemic Value Functions for Optimistic Exploration","created":"2026-09-28","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}