{"total":13,"rows":[{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2109.03970","title":"PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2201.11463","title":"Quantile-Based Policy Optimization for Reinforcement Learning","created":"2022-01-27","cited_by_count":8,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2210.00596","title":"Policy Gradients for Probabilistic Constrained Reinforcement Learning","created":"2022-10-02","cited_by_count":5,"area":null},{"id":"2205.15953","title":"Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2206.07483","title":"Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2109.11542","title":"ADVERSARIALuscator: An Adversarial-DRL Based Obfuscator and Metamorphic Malware SwarmGenerator","created":"2021-09-23","cited_by_count":1,"area":null},{"id":"2210.01344","title":"Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2203.01075","title":"Reliable validation of Reinforcement Learning Benchmarks","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2205.13130","title":"RACE: A Reinforcement Learning Framework for Improved Adaptive Control of NoC Channel Buffers","created":"2022-05-26","cited_by_count":0,"area":null}],"next_cursor":null}