{"total":242,"rows":[{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2409.18197","title":"Autonomous Network Defence using Reinforcement Learning","created":"2024-09-26","cited_by_count":15,"area":"deeprl"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2402.07411","title":"Potential-Based Reward Shaping For Intrinsic Motivation","created":"2024-02-12","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"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":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2408.15332","title":"What makes math problems hard for reinforcement learning: a case study","created":"2024-08-27","cited_by_count":9,"area":"deeprl"},{"id":"2410.11251","title":"Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning","created":"2024-10-15","cited_by_count":9,"area":"deeprl"},{"id":"2402.01361","title":"To the Max: Reinventing Reward in Reinforcement Learning","created":"2024-02-02","cited_by_count":8,"area":"deeprl"},{"id":"2404.09946","title":"A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning","created":"2024-04-15","cited_by_count":8,"area":"deeprl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.23631","title":"Intrinsically-Motivated Humans and Agents in Open-World Exploration","created":"2025-03-31","cited_by_count":8,"area":"deeprl"},{"id":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","cited_by_count":8,"area":"deeprl"},{"id":"2403.20109","title":"Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation","created":"2024-03-29","cited_by_count":7,"area":"deeprl"},{"id":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6,"area":"deeprl"},{"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":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2506.09270","title":"Uncertainty Prioritized Experience Replay","created":"2025-06-10","cited_by_count":6,"area":"deeprl"},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2406.16255","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","created":"2024-06-24","cited_by_count":5,"area":"deeprl"},{"id":"2408.09974","title":"The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective","created":"2024-08-19","cited_by_count":5,"area":"deeprl"},{"id":"2410.12136","title":"Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration","created":"2024-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2502.03752","title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","created":"2025-02-06","cited_by_count":5,"area":"deeprl"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2604.25416","title":"Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models","created":"2026-04-28","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":"2405.17243","title":"Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning","created":"2024-05-27","cited_by_count":4,"area":"deeprl"},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","cited_by_count":4,"area":"deeprl"},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2410.06621","title":"Effective Exploration Based on the Structural Information Principles","created":"2024-10-09","cited_by_count":4,"area":"deeprl"},{"id":"2507.13181","title":"Spectral Bellman Method: Unifying Representation and Exploration in RL","created":"2025-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2507.14748","title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","created":"2025-07-19","cited_by_count":4,"area":"deeprl"},{"id":"2601.19624","title":"Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2401.15484","title":"R$\\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training","created":"2024-01-27","cited_by_count":3,"area":"deeprl"},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2402.03138","title":"Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations","created":"2024-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2402.04539","title":"Learning Diverse Policies with Soft Self-Generated Guidance","created":"2024-02-07","cited_by_count":3,"area":"deeprl"},{"id":"2404.02235","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","created":"2024-04-02","cited_by_count":3,"area":"deeprl"},{"id":"2405.07473","title":"Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle","created":"2024-05-13","cited_by_count":3,"area":"deeprl"},{"id":"2405.11740","title":"Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2407.15083","title":"Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning","created":"2024-07-21","cited_by_count":3,"area":"deeprl"},{"id":"2407.21338","title":"Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks","created":"2024-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2408.07877","title":"BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2408.09237","title":"QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement Learning","created":"2024-08-17","cited_by_count":3,"area":"deeprl"},{"id":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2410.12197","title":"Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2501.17842","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","created":"2025-01-29","cited_by_count":3,"area":"deeprl"},{"id":"2503.04931","title":"Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation","created":"2025-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2505.11661","title":"Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2506.00138","title":"Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics","created":"2025-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2507.00358","title":"Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2507.07323","title":"Optimizing Model Splitting and Device Task Assignment for Deceptive Signal Assisted Private Multi-hop Split Learning","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2508.00152","title":"GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2602.04809","title":"Beyond Rewards in Reinforcement Learning for Cyber Defence","created":"2026-02-04","cited_by_count":3,"area":"deeprl"},{"id":"2603.14608","title":"Delightful Policy Gradient","created":"2026-03-15","cited_by_count":3,"area":"deeprl"},{"id":"2401.11372","title":"Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot","created":"2024-01-21","cited_by_count":2,"area":"deeprl"},{"id":"2402.00085","title":"Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning","created":"2024-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2403.06880","title":"Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning","created":"2024-03-11","cited_by_count":2,"area":"deeprl"},{"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":"2408.08446","title":"Lifelong Reinforcement Learning via Neuromodulation","created":"2024-08-15","cited_by_count":2,"area":"deeprl"},{"id":"2410.05225","title":"ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control","created":"2024-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2412.03800","title":"ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2412.13106","title":"Active Reinforcement Learning Strategies for Offline Policy Improvement","created":"2024-12-17","cited_by_count":2,"area":"deeprl"},{"id":"2501.19128","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","created":"2025-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2505.06182","title":"Apple: Toward General Active Perception via Reinforcement Learning","created":"2025-05-09","cited_by_count":2,"area":"deeprl"},{"id":"2505.12611","title":"Action-Dependent Optimality-Preserving Reward Shaping","created":"2025-05-19","cited_by_count":2,"area":"deeprl"},{"id":"2506.05418","title":"Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2507.02639","title":"On Efficient Bayesian Exploration in Model-Based Reinforcement Learning","created":"2025-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2509.25438","title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","created":"2025-09-29","cited_by_count":2,"area":"deeprl"},{"id":"2510.05996","title":"Information-Theoretic Policy Pre-Training with Empowerment","created":"2025-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2602.08092","title":"Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities","created":"2026-02-08","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}