{"total":60,"rows":[{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2109.10129","title":"Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits","created":"2021-09-21","cited_by_count":38,"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":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2210.06601","title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"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":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2312.01203","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","created":"2023-12-02","cited_by_count":11,"area":"wm"},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10,"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":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","cited_by_count":8,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2310.06089","title":"Predictive auxiliary objectives in deep RL mimic learning in the brain","created":"2023-10-09","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":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2201.12929","title":"The Geometry of Robust Value Functions","created":"2022-01-30","cited_by_count":6,"area":null},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","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":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2204.00565","title":"What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy","created":"2022-04-01","cited_by_count":5,"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":"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":"2206.05809","title":"Geometric Policy Iteration for Markov Decision Processes","created":"2022-06-12","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":"2407.06712","title":"MDP Geometry, Normalization and Reward Balancing Solvers","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2210.14361","title":"Auxiliary task discovery through generate-and-test","created":"2022-10-25","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":"2311.17855","title":"Maximum Entropy Model Correction in Reinforcement Learning","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2603.04333","title":"What Does Flow Matching Bring To TD Learning?","created":"2026-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2303.01391","title":"The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2306.08537","title":"VIBR: Learning View-Invariant Value Functions for Robust Visual Control","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2406.03731","title":"Quality-Diversity with Limited Resources","created":"2024-06-06","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":"2509.17092","title":"On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark","created":"2025-09-21","cited_by_count":1,"area":"deeprl"},{"id":"2606.01868","title":"Task-Induced Representational Invariances Depend on Learning Objective in Deep RL","created":"2026-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2609.36473","title":"Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2409.13108","title":"Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning","created":"2024-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2509.19159","title":"Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions","created":"2025-09-23","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":"2603.07833","title":"Gradient Iterated Temporal-Difference Learning","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2605.00787","title":"SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.16030","title":"Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.03382","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2609.22088","title":"Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}