{"total":25,"rows":[{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2109.05490","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","created":"2021-09-12","cited_by_count":35,"area":null},{"id":"2104.06521","title":"TAAC: Temporally Abstract Actor-Critic for Continuous Control","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2203.16707","title":"Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuits","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2311.15341","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2108.13525","title":"Identifying optimal cycles in quantum thermal machines with reinforcement-learning","created":"2021-08-30","cited_by_count":6,"area":null},{"id":"2111.01510","title":"A Hybrid Approach for Learning to Shift and Grasp with Elaborate Motion Primitives","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2104.10610","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2110.03760","title":"Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces","created":"2021-10-07","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":"2203.04927","title":"Investigation of Factorized Optical Flows as Mid-Level Representations","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2601.17582","title":"GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design","created":"2026-01-24","cited_by_count":2,"area":null},{"id":"2204.04785","title":"Model-free optimization of power/efficiency tradeoffs in quantum thermal machines using reinforcement learning","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2303.02731","title":"Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality","created":"2023-03-05","cited_by_count":1,"area":null},{"id":"2310.07724","title":"Visual Forecasting as a Mid-level Representation for Avoidance","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2408.15328","title":"Artificially intelligent Maxwell's demon for optimal control of open quantum systems","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2606.10601","title":"Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2204.00306","title":"Building Decision Forest via Deep Reinforcement Learning","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2206.05108","title":"Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy","created":"2022-06-10","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":"2209.11259","title":"Computational Discovery of Energy-Efficient Heat Treatment for Microstructure Design using Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":0,"area":null},{"id":"2312.05674","title":"Position control of an acoustic cavitation bubble by reinforcement learning","created":"2023-12-09","cited_by_count":0,"area":null},{"id":"2510.01508","title":"Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2606.26574","title":"Revisiting Action Factorization for Complex Action Spaces","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.07498","title":"Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}