{"total":135,"rows":[{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2406.12505","title":"Demonstrating Agile Flight from Pixels without State Estimation","created":"2024-06-18","cited_by_count":31,"area":"deeprl"},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"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":"2408.14336","title":"Equivariant Reinforcement Learning under Partial Observability","created":"2024-08-26","cited_by_count":18,"area":"deeprl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2501.14377","title":"Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight","created":"2025-01-24","cited_by_count":15,"area":"deeprl"},{"id":"2405.17416","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","created":"2024-05-27","cited_by_count":14,"area":"deeprl"},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2404.07950","title":"Reinforcement Learning with Generalizable Gaussian Splatting","created":"2024-03-18","cited_by_count":13,"area":"deeprl"},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2403.10940","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","created":"2024-03-16","cited_by_count":12,"area":"deeprl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2401.13362","title":"TraKDis: A Transformer-based Knowledge Distillation Approach for Visual Reinforcement Learning with Application to Cloth Manipulation","created":"2024-01-24","cited_by_count":8,"area":"deeprl"},{"id":"2401.17032","title":"M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation","created":"2024-01-30","cited_by_count":8,"area":"deeprl"},{"id":"2404.14064","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8,"area":"deeprl"},{"id":"2403.16369","title":"Learning Action-based Representations Using Invariance","created":"2024-03-25","cited_by_count":7,"area":"deeprl"},{"id":"2404.12754","title":"Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation","created":"2024-04-19","cited_by_count":7,"area":"deeprl"},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2412.13662","title":"When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2406.02370","title":"Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2407.00633","title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","created":"2024-06-30","cited_by_count":6,"area":"deeprl"},{"id":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2402.12181","title":"Revisiting Data Augmentation in Deep Reinforcement Learning","created":"2024-02-19","cited_by_count":5,"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":"2408.03768","title":"HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks","created":"2024-08-07","cited_by_count":5,"area":"deeprl"},{"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":"2410.09972","title":"Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions","created":"2024-10-13","cited_by_count":5,"area":"deeprl"},{"id":"2410.18800","title":"PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds","created":"2024-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2505.10646","title":"Accelerating Visual-Policy Learning through Parallel Differentiable Simulation","created":"2025-05-15","cited_by_count":5,"area":"deeprl"},{"id":"2510.21609","title":"Enhancing Tactile-based Reinforcement Learning for Robotic Control","created":"2025-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2605.06500","title":"Operator-Guided Invariance Learning for Continuous Reinforcement Learning","created":"2026-05-07","cited_by_count":5,"area":"deeprl"},{"id":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","cited_by_count":4,"area":"deeprl"},{"id":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2412.14312","title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2504.16591","title":"JEPA for RL: Investigating Joint-Embedding Predictive Architectures for Reinforcement Learning","created":"2025-04-23","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":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2401.11512","title":"TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning","created":"2024-01-21","cited_by_count":3,"area":"deeprl"},{"id":"2403.04588","title":"Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace","created":"2024-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","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":"2409.01646","title":"BEVNav: Robot Autonomous Navigation Via Spatial-Temporal Contrastive Learning in Bird's-Eye View","created":"2024-09-03","cited_by_count":3,"area":"deeprl"},{"id":"2409.02714","title":"MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning","created":"2024-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.12983","title":"Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2410.14038","title":"Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning","created":"2024-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2411.06174","title":"State Chrono Representation for Enhancing Generalization in Reinforcement Learning","created":"2024-11-09","cited_by_count":3,"area":"deeprl"},{"id":"2502.02834","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","created":"2025-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2504.14805","title":"Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment","created":"2025-04-21","cited_by_count":3,"area":"deeprl"},{"id":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2507.18519","title":"Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning","created":"2025-07-24","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2403.17266","title":"Exploring CausalWorld: Enhancing robotic manipulation via knowledge transfer and curriculum learning","created":"2024-03-25","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":"2409.17992","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","created":"2024-09-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2505.04619","title":"Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation","created":"2025-05-07","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":"2507.06326","title":"Sample-Efficient Reinforcement Learning Controller for Deep Brain Stimulation in Parkinson's Disease","created":"2025-07-08","cited_by_count":2,"area":"deeprl"},{"id":"2511.11607","title":"Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"deeprl"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2602.12636","title":"Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL","created":"2026-02-13","cited_by_count":2,"area":"deeprl"},{"id":"2602.21203","title":"Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2603.02008","title":"Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards","created":"2026-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2603.18257","title":"Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning","created":"2026-03-18","cited_by_count":2,"area":"deeprl"},{"id":"2405.10576","title":"An Efficient Learning Control Framework With Sim-to-Real for String-Type Artificial Muscle-Driven Robotic Systems","created":"2024-05-17","cited_by_count":1,"area":"deeprl"},{"id":"2406.04815","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","created":"2024-06-07","cited_by_count":1,"area":"deeprl"},{"id":"2406.12359","title":"Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents","created":"2024-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2407.21546","title":"Black Box Meta-Learning Intrinsic Rewards","created":"2024-07-31","cited_by_count":1,"area":"deeprl"},{"id":"2409.17411","title":"Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2410.23434","title":"Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2502.01316","title":"Learning Fused State Representations for Control from Multi-View Observations","created":"2025-02-03","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2510.05692","title":"Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies","created":"2025-10-07","cited_by_count":1,"area":"deeprl"},{"id":"2510.06138","title":"Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks","created":"2025-10-07","cited_by_count":1,"area":"deeprl"},{"id":"2510.08442","title":"Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning","created":"2025-10-09","cited_by_count":1,"area":"deeprl"},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2602.18724","title":"Task-Aware Exploration via a Predictive Bisimulation Metric","created":"2026-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2603.02104","title":"ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation","created":"2026-03-02","cited_by_count":1,"area":"deeprl"},{"id":"2603.08558","title":"Impact of Connectivity on Laplacian Representations in Reinforcement Learning","created":"2026-03-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.09364","title":"MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","created":"2026-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.25267","title":"Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning","created":"2026-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2605.26478","title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","created":"2026-05-26","cited_by_count":1,"area":"deeprl"},{"id":"2402.07412","title":"Auxiliary Reward Generation with Transition Distance Representation Learning","created":"2024-02-12","cited_by_count":0,"area":"deeprl"},{"id":"2405.02598","title":"UDUC: An Uncertainty-driven Approach for Learning-based Robust Control","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2405.19736","title":"Intrinsic Dynamics-Driven Generalizable Scene Representations for Vision-Oriented Decision-Making Applications","created":"2024-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2407.01570","title":"Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL","created":"2024-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2407.11044","title":"Generalizing soft actor-critic algorithms to discrete action spaces","created":"2024-07-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}