{"total":26,"rows":[{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2210.07424","title":"Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2401.13231","title":"DittoGym: Learning to Control Soft Shape-Shifting Robots","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2303.13320","title":"QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation","created":"2023-03-23","cited_by_count":5,"area":null},{"id":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2102.13195","title":"Reinforcement Learning of Implicit and Explicit Control Flow in Instructions","created":"2021-02-25","cited_by_count":4,"area":null},{"id":"2407.05789","title":"CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2510.23535","title":"Sequential Multi-Agent Dynamic Algorithm Configuration","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2308.10203","title":"Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2506.12932","title":"Complexity Scaling Laws for Neural Models using Combinatorial Optimization","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2511.02314","title":"Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2207.12509","title":"Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs","created":"2022-07-25","cited_by_count":0,"area":null},{"id":"2208.14447","title":"A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space","created":"2022-08-30","cited_by_count":0,"area":null},{"id":"2209.01876","title":"SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2212.11709","title":"Reinforcement Learning Based Approaches to Adaptive Context Caching in Distributed Context Management Systems","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2308.14523","title":"Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2406.11128","title":"Model Adaptation for Time Constrained Embodied Control","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2409.18735","title":"Autoregressive Policy Optimization for Constrained Allocation Tasks","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2502.00288","title":"Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network","created":"2025-02-01","cited_by_count":0,"area":null}],"next_cursor":null}