{"total":23,"rows":[{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2310.13565","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","created":"2023-10-20","cited_by_count":19,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2212.03175","title":"Learning Representations that Enable Generalization in Assistive Tasks","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2409.12798","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2311.10026","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2509.24129","title":"Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2307.05209","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2309.14096","title":"Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2310.10610","title":"Quantifying Assistive Robustness Via the Natural-Adversarial Frontier","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2504.19480","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2307.09109","title":"Mining of Single-Class by Active Learning for Semantic Segmentation","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2503.24296","title":"Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2510.15796","title":"Cavity Duplexer Tuning with 1d Resnet-like Neural Networks","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2607.17317","title":"TAPAS: Throughput-adaptive Perception for Autonomous Systems","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.11239","title":"Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}