{"total":40,"rows":[{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"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":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"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":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2305.03942","title":"HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation","created":"2023-05-06","cited_by_count":29,"area":null},{"id":"2111.07171","title":"Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning","created":"2021-11-13","cited_by_count":24,"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":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2504.00420","title":"Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2111.07183","title":"Reliably-stabilizing piecewise-affine neural network controllers","created":"2021-11-13","cited_by_count":13,"area":null},{"id":"2101.04422","title":"Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning","created":"2021-01-12","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":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"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":"2211.15068","title":"Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search","created":"2022-11-28","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":"2202.12967","title":"Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates","created":"2022-02-25","cited_by_count":2,"area":null},{"id":"2205.05061","title":"On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer","created":"2022-05-10","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":"2103.05174","title":"Learning to Play Soccer From Scratch: Sample-Efficient Emergent Coordination through Curriculum-Learning and Competition","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2204.13209","title":"Robust stabilization of polytopic systems via fast and reliable neural network-based approximations","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2303.01170","title":"Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2502.05526","title":"Towards Learning Scalable Agile Dynamic Motion Planning for Robosoccer Teams with Policy Optimization","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2102.06632","title":"Deep Reinforcement Learning for Backup Strategies against Adversaries","created":"2021-02-12","cited_by_count":0,"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":"2108.12537","title":"An Anytime Hierarchical Approach for Stochastic Task and Motion Planning","created":"2021-08-28","cited_by_count":0,"area":null},{"id":"2206.01663","title":"Joint Energy Dispatch and Unit Commitment in Microgrids Based on Deep Reinforcement Learning","created":"2022-06-03","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":"2301.03358","title":"Cost-Effective Two-Stage Network Slicing for Edge-Cloud Orchestrated Vehicular Networks","created":"2022-12-31","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":"2501.15495","title":"Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning","created":"2025-01-26","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":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","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}],"next_cursor":null}