{"total":10,"rows":[{"id":"2111.04146","title":"Optimization of the Model Predictive Control Meta-Parameters Through Reinforcement Learning","created":"2021-11-07","cited_by_count":7,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2211.11620","title":"Simultaneously Updating All Persistence Values in Reinforcement Learning","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2305.18701","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2309.13349","title":"Speeding-up Evolutionary Algorithms to solve Black-Box Optimization Problems","created":"2023-09-23","cited_by_count":2,"area":null},{"id":"2301.00723","title":"Temporally Layered Architecture for Adaptive, Distributed and Continuous Control","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2308.04299","title":"Actor-Critic with variable time discretization via sustained actions","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2310.09412","title":"Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2610.04810","title":"Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}