{"total":33,"rows":[{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"area":null},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65,"area":null},{"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":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31,"area":null},{"id":"2110.11960","title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models","created":"2021-10-22","cited_by_count":25,"area":null},{"id":"2402.15025","title":"Practice Makes Perfect: Planning to Learn Skill Parameter Policies","created":"2024-02-22","cited_by_count":23,"area":null},{"id":"2109.06449","title":"Deep hierarchical reinforcement agents for automated penetration testing","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2210.12250","title":"STAP: Sequencing Task-Agnostic Policies","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2302.03225","title":"Efficient XAI Techniques: A Taxonomic Survey","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2104.07294","title":"Generalising Discrete Action Spaces with Conditional Action Trees","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2111.06726","title":"One model Packs Thousands of Items with Recurrent Conditional Query Learning","created":"2021-11-12","cited_by_count":5,"area":null},{"id":"2111.13667","title":"TMM-Fast: A Transfer Matrix Computation Package for Multilayer Thin-Film Optimization","created":"2021-11-24","cited_by_count":5,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"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":"2103.10524","title":"Generalizing Object-Centric Task-Axes Controllers using Keypoints","created":"2021-03-18","cited_by_count":3,"area":null},{"id":"2107.10901","title":"A reinforcement learning approach to resource allocation in genomic selection","created":"2021-07-22","cited_by_count":3,"area":null},{"id":"2112.14553","title":"Active Learning of Quantum System Hamiltonians yields Query Advantage","created":"2021-12-29","cited_by_count":3,"area":null},{"id":"2211.06134","title":"Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2109.07703","title":"ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI","created":"2021-09-16","cited_by_count":2,"area":null},{"id":"2110.15799","title":"Guided Policy Search for Parameterized Skills using Adverbs","created":"2021-10-23","cited_by_count":2,"area":null},{"id":"2303.09628","title":"Efficient Learning of High Level Plans from Play","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2510.24095","title":"Learning Parameterized Skills from Demonstrations","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2105.00499","title":"Curious Exploration and Return-based Memory Restoration for Deep Reinforcement Learning","created":"2021-05-02","cited_by_count":0,"area":null},{"id":"2305.01461","title":"Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management","created":"2023-05-02","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":"2509.13127","title":"Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2511.16075","title":"A Hybrid Proactive And Predictive Framework For Edge Cloud Resource Management","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.18716","title":"Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2606.16014","title":"Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.18820","title":"When to Commit and When to Defer: Maturing Markov Decision Processes under Refining Information and Expiring Opportunities","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.25246","title":"ShuttleArena: Interpretable Self-Play in Physics-Based Badminton","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}