{"total":57,"rows":[{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"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":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"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":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44,"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":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"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":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"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":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2406.17718","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","created":"2024-06-25","cited_by_count":14,"area":"deeprl"},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2402.13425","title":"Investigating the Histogram Loss in Regression","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","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":"2105.05985","title":"An Open-Source Multi-Goal Reinforcement Learning Environment for Robotic Manipulation with Pybullet","created":"2021-05-12","cited_by_count":7,"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":"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":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"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":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"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":"2205.00334","title":"Engineering flexible machine learning systems by traversing functionally-invariant paths","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2311.03534","title":"PcLast: Discovering Plannable Continuous Latent States","created":"2023-11-06","cited_by_count":4,"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":"2306.01066","title":"Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning","created":"2023-06-01","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":"2306.16750","title":"Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2407.03436","title":"A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2211.16753","title":"VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations","created":"2022-11-30","cited_by_count":1,"area":null},{"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":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2407.16842","title":"Adapting Image-based RL Policies via Predicted Rewards","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2501.01114","title":"Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2507.00275","title":"Deep Double Q-learning","created":"2025-06-30","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":"2111.10103","title":"Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2203.10351","title":"The Sandbox Environment for Generalizable Agent Research (SEGAR)","created":"2022-03-19","cited_by_count":0,"area":null},{"id":"2302.13483","title":"CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2404.00886","title":"MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control","created":"2024-04-01","cited_by_count":0,"area":"deeprl"},{"id":"2406.01047","title":"An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing","created":"2024-06-03","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":"2601.13904","title":"PREFAB: PREFerence-based Affective Modeling for Low-Budget Self-Annotation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2607.06640","title":"What a World Model Represents Is Three Questions","created":"2026-07-07","cited_by_count":0,"area":"wm"}],"next_cursor":null}