{"total":34,"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":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2401.12224","title":"LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation","created":"2023-12-28","cited_by_count":40,"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":"2109.06449","title":"Deep hierarchical reinforcement agents for automated penetration testing","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2205.11854","title":"Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2206.06304","title":"Multi-user Co-inference with Batch Processing Capable Edge Server","created":"2022-06-03","cited_by_count":11,"area":null},{"id":"2207.12051","title":"Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks","created":"2022-07-25","cited_by_count":10,"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":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2408.08442","title":"A semi-centralized multi-agent RL framework for efficient irrigation scheduling","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2606.18308","title":"TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2306.04660","title":"Adaptive Frequency Green Light Optimal Speed Advisory based on Hybrid Actor-Critic Reinforcement Learning","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2510.13343","title":"AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions","created":"2025-10-15","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":"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":"2203.05079","title":"SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning","created":"2022-03-09","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":"2306.15913","title":"DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces","created":"2023-06-28","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":"2508.07804","title":"Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.14782","title":"TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.12716","title":"Joint AoI and Handover Optimization in Space-Air-Ground Integrated Network","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.23905","title":"Integrated Communication and Control for Energy-Efficient UAV Swarms: A Multi-Agent Reinforcement Learning Approach","created":"2025-09-28","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":"2601.12311","title":"Cross-reality location privacy protection in 6G-enabled vehicular metaverses: an LLM-enhanced hybrid generative diffusion model-based approach","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.22476","title":"RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning","created":"2026-01-30","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":"2606.26574","title":"Revisiting Action Factorization for Complex Action Spaces","created":"2026-06-25","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}