{"total":11,"rows":[{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2405.08403","title":"TFWT: Tabular Feature Weighting with Transformer","created":"2024-05-14","cited_by_count":12,"area":null},{"id":"2301.09159","title":"Abstracting Imperfect Information Away from Two-Player Zero-Sum Games","created":"2023-01-22","cited_by_count":6,"area":null},{"id":"2203.11656","title":"Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2304.13138","title":"The Update-Equivalence Framework for Decision-Time Planning","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2502.11457","title":"Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2311.14651","title":"History Filtering in Imperfect Information Games: Algorithms and Complexity","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2510.03614","title":"Neural Bayesian Filtering","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2303.12371","title":"$P^{3}O$: Transferring Visual Representations for Reinforcement Learning via Prompting","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2306.04440","title":"Dual policy as self-model for planning","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2312.01267","title":"Distributed Reinforcement Learning for Molecular Design: Antioxidant case","created":"2023-12-03","cited_by_count":0,"area":null}],"next_cursor":null}