{"total":56,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121,"area":null},{"id":"2308.07498","title":"DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation","created":"2023-08-14","cited_by_count":85,"area":"wm"},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68,"area":"wm"},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2106.04152","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41,"area":null},{"id":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"area":"diffusion"},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31,"area":null},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"area":null},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2106.11719","title":"Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers","created":"2021-06-22","cited_by_count":22,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"id":"2205.07886","title":"An Empirical Investigation of Representation Learning for Imitation","created":"2022-05-16","cited_by_count":15,"area":"offlinerl"},{"id":"2112.15303","title":"SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning","created":"2021-12-31","cited_by_count":14,"area":null},{"id":"2302.12003","title":"Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions","created":"2023-02-12","cited_by_count":14,"area":null},{"id":"2204.04905","title":"Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels","created":"2022-04-11","cited_by_count":13,"area":null},{"id":"2203.01810","title":"Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2110.04935","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","created":"2021-10-11","cited_by_count":10,"area":null},{"id":"2207.13224","title":"PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations","created":"2022-07-27","cited_by_count":10,"area":null},{"id":"2211.11116","title":"Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation","created":"2022-11-20","cited_by_count":9,"area":null},{"id":"2305.16379","title":"Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning","created":"2023-05-25","cited_by_count":8,"area":null},{"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":"2206.11396","title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2102.04897","title":"Learning State Representations from Random Deep Action-conditional Predictions","created":"2021-02-09","cited_by_count":6,"area":null},{"id":"2210.08217","title":"PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2510.21609","title":"Enhancing Tactile-based Reinforcement Learning for Robotic Control","created":"2025-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"area":null},{"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":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2201.07016","title":"Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2204.00888","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","created":"2022-04-02","cited_by_count":3,"area":null},{"id":"2303.03787","title":"Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2411.06174","title":"State Chrono Representation for Enhancing Generalization in Reinforcement Learning","created":"2024-11-09","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":"2211.00086","title":"Disentangled (Un)Controllable Features","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2303.04218","title":"Deep Occupancy-Predictive Representations for Autonomous Driving","created":"2023-03-07","cited_by_count":1,"area":"driving"},{"id":"2310.07724","title":"Visual Forecasting as a Mid-level Representation for Avoidance","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2209.05333","title":"Rollout Total Correlation for Deep Reinforcement Learning","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2209.09441","title":"Locally Constrained Representations in Reinforcement Learning","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2505.16734","title":"Maximum Total Correlation Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2510.10744","title":"How Patterns Dictate Learnability in Sequential Data","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2606.05555","title":"Representation Learning Enables Scalable Multitask Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}