{"total":19,"rows":[{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2305.16483","title":"Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2310.15888","title":"State Sequences Prediction via Fourier Transform for Representation Learning","created":"2023-10-24","cited_by_count":7,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2312.15863","title":"PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2312.04371","title":"A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2108.12842","title":"DASHA: Decentralized Autofocusing System with Hierarchical Agents","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2310.04241","title":"Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2507.11486","title":"Exploring the robustness of TractOracle methods in RL-based tractography","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2310.05099","title":"Intelligent DRL-Based Adaptive Region of Interest for Delay-sensitive Telemedicine Applications","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2501.08423","title":"LiLaN: A Linear Latent Network as the Solution Operator for Real-Time Solutions to Stiff Nonlinear Ordinary Differential Equations","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2602.12520","title":"Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2608.06015","title":"ProDVI: Programmatic Dynamics Priors for Value Network Initialization","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}