{"total":17,"rows":[{"id":"2403.13765","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","created":"2024-03-20","cited_by_count":10,"area":"deeprl"},{"id":"2404.09946","title":"A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning","created":"2024-04-15","cited_by_count":8,"area":"deeprl"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.07253","title":"Hybrid Reinforcement Learning from Offline Observation Alone","created":"2024-06-11","cited_by_count":5,"area":"deeprl"},{"id":"2406.11640","title":"Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions","created":"2024-06-17","cited_by_count":4,"area":"deeprl"},{"id":"2510.03207","title":"To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning","created":"2025-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2404.14552","title":"Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs","created":"2024-04-22","cited_by_count":2,"area":"deeprl"},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2410.23434","title":"Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2503.02030","title":"Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation","created":"2025-03-03","cited_by_count":1,"area":"deeprl"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2405.15829","title":"Spatio-temporal Value Semantics-based Abstraction for Dense Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2408.13498","title":"Rethinking State Disentanglement in Causal Reinforcement Learning","created":"2024-08-24","cited_by_count":0,"area":"deeprl"},{"id":"2507.04187","title":"Where to Intervene: Action Selection in Deep Reinforcement Learning","created":"2025-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2603.23461","title":"End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions","created":"2026-03-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.02928","title":"Towards Scaling Reinforcement Learning to Massive Populations: Learning Mean-Field Representations","created":"2026-08-26","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}