{"total":24,"rows":[{"id":"2203.02628","title":"Target Network and Truncation Overcome The Deadly Triad in $Q$-Learning","created":"2022-03-05","cited_by_count":31,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2202.06828","title":"On the Convergence of SARSA with Linear Function Approximation","created":"2022-02-14","cited_by_count":15,"area":null},{"id":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2302.12537","title":"Why Target Networks Stabilise Temporal Difference Methods","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2202.12504","title":"Consolidated Adaptive T-soft Update for Deep Reinforcement Learning","created":"2022-02-25","cited_by_count":5,"area":null},{"id":"2203.11489","title":"A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle","created":"2022-03-22","cited_by_count":4,"area":null},{"id":"2309.16819","title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2111.11758","title":"The Impact of Data Distribution on Q-learning with Function Approximation","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2210.12282","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2402.15819","title":"Debiased Model-based Interactive Recommendation","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2501.11921","title":"Goal-oriented Transmission Scheduling: Structure-guided DRL with a Unified Dual On-policy and Off-policy Approach","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2503.11452","title":"Deep Learning Agents Trained For Avoidance Behave Like Hawks And Doves","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2605.28849","title":"Behavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy Prediction","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}