{"total":80,"rows":[{"id":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56,"area":"deeprl"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"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":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"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":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"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":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8,"area":"deeprl"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","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":"2407.09247","title":"Constrained Intrinsic Motivation for Reinforcement Learning","created":"2024-07-12","cited_by_count":6,"area":"deeprl"},{"id":"2509.11125","title":"ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations","created":"2025-09-14","cited_by_count":5,"area":"deeprl"},{"id":"2402.07102","title":"An Empirical Study on the Power of Future Prediction in Partially Observable Environments","created":"2024-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2404.10883","title":"Automated Discovery of Functional Actual Causes in Complex Environments","created":"2024-04-16","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":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","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":"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":"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":"2409.02714","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":"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":"2502.06825","title":"RLOMM: An Efficient and Robust Online Map Matching Framework with Reinforcement Learning","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":"2508.00152","title":"GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2510.02484","title":"From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning","created":"2025-10-02","cited_by_count":3,"area":"deeprl"},{"id":"2510.14117","title":"ViTacGen: Robotic Pushing with Vision-to-Touch Generation","created":"2025-10-15","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":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2608.30640","title":"Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL","created":"2026-08-31","cited_by_count":3,"area":"deeprl"},{"id":"2402.11317","title":"Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics","created":"2024-02-17","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":"2502.05555","title":"Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder","created":"2025-02-08","cited_by_count":2,"area":"deeprl"},{"id":"2502.12624","title":"Implicit Repair with Reinforcement Learning in Emergent Communication","created":"2025-02-18","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":"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":"2406.04815","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","created":"2024-06-07","cited_by_count":1,"area":"deeprl"},{"id":"2411.01425","title":"Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning","created":"2024-11-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.05980","title":"AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification","created":"2025-06-06","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":"2604.15414","title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","created":"2026-04-16","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":"2607.00392","title":"Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL","created":"2026-07-01","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":"2408.14009","title":"Optimizing TD3 for 7-DOF Robotic Arm Grasping: Overcoming Suboptimality with Exploration-Enhanced Contrastive Learning","created":"2024-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2503.00227","title":"The Learning Approach to Games","created":"2025-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2504.04164","title":"MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning","created":"2025-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2505.16734","title":"Maximum Total Correlation Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2505.17830","title":"Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning","created":"2025-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2506.11967","title":"Visual Pre-Training on Unlabeled Images using Reinforcement Learning","created":"2025-06-13","cited_by_count":0,"area":"deeprl"},{"id":"2509.04970","title":"DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation","created":"2025-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2510.22039","title":"Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability","created":"2025-10-24","cited_by_count":0,"area":"deeprl"},{"id":"2510.25679","title":"Navigation in a Three-Dimensional Urban Flow using Deep Reinforcement Learning","created":"2025-10-29","cited_by_count":0,"area":"deeprl"},{"id":"2511.16929","title":"CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.19810","title":"Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.21394","title":"Towards Space-Based Environmentally-Adaptive Grasping","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2602.09396","title":"Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2603.14887","title":"ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning","created":"2026-03-16","cited_by_count":0,"area":"deeprl"},{"id":"2603.24930","title":"CROSS: A Mixture-of-Experts Reinforcement Learning Framework for Generalizable Large-Scale Traffic Signal Control","created":"2026-03-26","cited_by_count":0,"area":"deeprl"},{"id":"2604.21130","title":"Self-Predictive Representation for Autonomous UAV Object-Goal Navigation","created":"2026-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.13554","title":"Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.14026","title":"R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.24352","title":"Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.11525","title":"Learning Object Manipulation from Scratch via Contrastive Interaction","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.21271","title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2607.13498","title":"Factorized Spectral Representations for Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.26571","title":"Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.36238","title":"ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.20009","title":"Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}