{"total":102,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2105.08054","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","created":"2021-05-17","cited_by_count":85,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75,"area":null},{"id":"2104.04112","title":"Auxiliary Tasks and Exploration Enable ObjectNav","created":"2021-04-08","cited_by_count":74,"area":null},{"id":"2110.14565","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","created":"2021-10-27","cited_by_count":74,"area":"wm"},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58,"area":"deeprl"},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"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":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"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":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2102.10106","title":"Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction","created":"2021-02-19","cited_by_count":36,"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":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"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":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2510.00739","title":"TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning","created":"2025-10-01","cited_by_count":22,"area":"deeprl"},{"id":"2107.08577","title":"Structured World Belief for Reinforcement Learning in POMDP","created":"2021-07-19","cited_by_count":21,"area":"wm"},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2111.02338","title":"Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity","created":"2021-11-03","cited_by_count":18,"area":null},{"id":"2201.00248","title":"Transfer RL across Observation Feature Spaces via Model-Based Regularization","created":"2022-01-01","cited_by_count":18,"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":"2210.05064","title":"VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement","created":"2022-10-11","cited_by_count":18,"area":null},{"id":"2406.01968","title":"Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment","created":"2024-06-04","cited_by_count":18,"area":null},{"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":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2205.07886","title":"An Empirical Investigation of Representation Learning for Imitation","created":"2022-05-16","cited_by_count":15,"area":"offlinerl"},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2102.02337","title":"Environment Predictive Coding for Embodied Agents","created":"2021-02-03","cited_by_count":12,"area":null},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2304.02639","title":"ENTL: Embodied Navigation Trajectory Learner","created":"2023-04-05","cited_by_count":11,"area":"wm"},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2306.11488","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","created":"2023-06-20","cited_by_count":11,"area":"wm"},{"id":"2110.04935","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","created":"2021-10-11","cited_by_count":10,"area":null},{"id":"2305.01521","title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2406.04853","title":"Time-Series JEPA for Predictive Remote Control under Capacity-Limited Networks","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2205.14557","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2306.04244","title":"Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Images","created":"2023-06-07","cited_by_count":7,"area":null},{"id":"2310.15888","title":"State Sequences Prediction via Fourier Transform for Representation Learning","created":"2023-10-24","cited_by_count":7,"area":null},{"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":"2406.02035","title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","created":"2024-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2505.03176","title":"seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models","created":"2025-05-06","cited_by_count":7,"area":"wm"},{"id":"2102.04897","title":"Learning State Representations from Random Deep Action-conditional Predictions","created":"2021-02-09","cited_by_count":6,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2204.02877","title":"PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2501.19116","title":"A Theoretical Justification for Asymmetric Actor-Critic Algorithms","created":"2025-01-31","cited_by_count":6,"area":"deeprl"},{"id":"2209.10901","title":"Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2410.00350","title":"Efficient Training of Large Vision Models via Advanced Automated Progressive Learning","created":"2024-09-06","cited_by_count":5,"area":"diffusion"},{"id":"2206.07041","title":"Learning Behavior Representations Through Multi-Timescale Bootstrapping","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2303.08811","title":"Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis","created":"2023-03-15","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":"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":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2305.18491","title":"Towards a Better Understanding of Representation Dynamics under TD-learning","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2308.11331","title":"GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"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":"2503.13431","title":"Measuring In-Context Computation Complexity via Hidden State Prediction","created":"2025-03-17","cited_by_count":3,"area":null},{"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":"2608.12939","title":"Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency","created":"2026-08-13","cited_by_count":3,"area":"wm"},{"id":"2106.05139","title":"Pretrained Encoders are All You Need","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2112.01163","title":"Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2211.06733","title":"Deep Reinforcement Learning with Vector Quantized Encoding","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2309.02583","title":"Representation Learning for Sequential Volumetric Design Tasks","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2407.20651","title":"Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations","created":"2024-07-30","cited_by_count":2,"area":"deeprl"},{"id":"2509.26000","title":"Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access","created":"2025-09-30","cited_by_count":2,"area":"deeprl"},{"id":"2112.08929","title":"Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2303.04218","title":"Deep Occupancy-Predictive Representations for Autonomous Driving","created":"2023-03-07","cited_by_count":1,"area":"driving"},{"id":"2304.13892","title":"Discovering Object-Centric Generalized Value Functions From Pixels","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2109.08642","title":"POAR: Efficient Policy Optimization via Online Abstract State Representation Learning","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2208.11349","title":"Dynamic Memory-based Curiosity: A Bootstrap Approach for Exploration","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2211.06236","title":"Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2310.18893","title":"Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation","created":"2023-10-29","cited_by_count":0,"area":"distill"},{"id":"2407.21359","title":"ProSpec RL: Plan Ahead, then Execute","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2408.02014","title":"Unsupervised Representation Learning by Balanced Self Attention Matching","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2506.02125","title":"Descriptive History Representations: Learning Representations by Answering Questions","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2606.21297","title":"NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2607.04153","title":"Mask-based Predictive Representations for Reinforcement Learning","created":"2026-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2607.26040","title":"Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance","created":"2026-07-28","cited_by_count":0,"area":"wm"}],"next_cursor":"100"}