{"total":45,"rows":[{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2501.19254","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set","created":"2025-01-31","cited_by_count":12,"area":"deeprl"},{"id":"2407.00286","title":"Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks","created":"2024-06-29","cited_by_count":8,"area":"deeprl"},{"id":"2505.02288","title":"Universal Approximation Theorem of Deep Q-Networks","created":"2025-05-04","cited_by_count":6,"area":"deeprl"},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"id":"2407.10454","title":"Deflated Dynamics Value Iteration","created":"2024-07-15","cited_by_count":5,"area":"deeprl"},{"id":"2412.05783","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","created":"2024-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2509.26442","title":"Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning","created":"2025-09-30","cited_by_count":5,"area":"deeprl"},{"id":"2405.04017","title":"An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks","created":"2024-05-07","cited_by_count":4,"area":"deeprl"},{"id":"2503.23308","title":"Reinforcement Learning for Active Matter","created":"2025-03-30","cited_by_count":4,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2401.15196","title":"Regularized Q-Learning with Linear Function Approximation","created":"2024-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2407.08803","title":"PID Accelerated Temporal Difference Algorithms","created":"2024-07-11","cited_by_count":2,"area":"deeprl"},{"id":"2409.18152","title":"Reinforcement Learning for Finite Space Mean-Field Type Games","created":"2024-09-25","cited_by_count":2,"area":"deeprl"},{"id":"2506.01261","title":"The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning","created":"2025-06-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.26026","title":"Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation","created":"2025-10-29","cited_by_count":2,"area":"deeprl"},{"id":"2602.20527","title":"A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2407.13279","title":"Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2408.11339","title":"Deep Reinforcement Learning for Decentralized Multi-Robot Control: A DQN Approach to Robustness and Information Integration","created":"2024-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2505.19058","title":"Distributionally Robust Deep Q-Learning","created":"2025-05-25","cited_by_count":1,"area":"deeprl"},{"id":"2505.22492","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","created":"2025-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2506.22851","title":"Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality","created":"2025-06-28","cited_by_count":1,"area":"deeprl"},{"id":"2510.03064","title":"Comparative Analysis of Parameterized Action Actor-Critic Reinforcement Learning Algorithms for Web Search Match Plan Generation","created":"2025-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2601.17247","title":"Learning Market Making with Closing Auctions","created":"2026-01-24","cited_by_count":1,"area":"deeprl"},{"id":"2603.10199","title":"Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2604.21863","title":"Replay-buffer engineering for noise-aware quantum circuit optimization","created":"2026-04-23","cited_by_count":1,"area":"deeprl"},{"id":"2401.07263","title":"BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions","created":"2024-01-14","cited_by_count":0,"area":"deeprl"},{"id":"2402.00468","title":"RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway","created":"2024-02-01","cited_by_count":0,"area":"deeprl"},{"id":"2402.11627","title":"Interactive Garment Recommendation with User in the Loop","created":"2024-02-18","cited_by_count":0,"area":"deeprl"},{"id":"2402.16899","title":"A priori Estimates for Deep Residual Network in Continuous-time Reinforcement Learning","created":"2024-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2403.03643","title":"A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation","created":"2024-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2405.02044","title":"Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2410.04518","title":"A Reinforcement Learning Engine with Reduced Action and State Space for Scalable Cyber-Physical Optimal Response","created":"2024-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2411.02559","title":"Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation","created":"2024-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2505.00382","title":"Approximation to Deep Q-Network by Stochastic Delay Differential Equations","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2509.02737","title":"Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient","created":"2025-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2509.24274","title":"Adversarial Reinforcement Learning Framework for ESP Cheater Simulation","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2602.03911","title":"The Role of Target Update Frequencies in Q-Learning","created":"2026-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2604.04394","title":"Finite-Time Analysis of Q-Value Iteration for General-Sum Stackelberg Games","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.06373","title":"Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\\tau$-Mixing","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.18979","title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.16846","title":"Deep Q-Learning on H\\\"older Spaces","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2609.27741","title":"Limiting-Kernel Q($\\lambda$): Bridging Short and Long Horizons","created":"2026-09-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}