{"total":13,"rows":[{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2412.10871","title":"Fully Test-time Adaptation for Tabular Data","created":"2024-12-14","cited_by_count":8,"area":null},{"id":"2307.02991","title":"ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocation","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2407.10784","title":"AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2103.14407","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2312.10642","title":"Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2205.07250","title":"A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2307.07529","title":"Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2409.13571","title":"Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2509.07633","title":"Variational Quantum Circuits in Offline Contextual Bandit Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2609.27244","title":"Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}