{"total":156,"rows":[{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225,"area":"mllm"},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"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":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"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":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"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":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","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":"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":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","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":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","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":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","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":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"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":"2107.09822","title":"Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"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":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"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":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2105.01593","title":"Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation","created":"2021-05-04","cited_by_count":15,"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":"2101.09458","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","created":"2021-01-23","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"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":"2603.15789","title":"Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning","created":"2026-03-16","cited_by_count":10,"area":"deeprl"},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2210.04642","title":"Exploration via Planning for Information about the Optimal Trajectory","created":"2022-10-06","cited_by_count":8,"area":null},{"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":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","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":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2406.09574","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","created":"2024-06-13","cited_by_count":6,"area":"alignment"},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2411.03932","title":"Improved Regret of Linear Ensemble Sampling","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2602.02555","title":"Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","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":"2302.03439","title":"Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"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":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","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":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2107.14698","title":"Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning","created":"2021-07-30","cited_by_count":3,"area":null},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2203.01004","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2210.01800","title":"Bayesian Q-learning With Imperfect Expert Demonstrations","created":"2022-10-01","cited_by_count":3,"area":null},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null}],"next_cursor":"100"}