{"total":19,"rows":[{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"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":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2410.05952","title":"Active Evaluation Acquisition for Efficient LLM Benchmarking","created":"2024-10-08","cited_by_count":35,"area":null},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2312.03009","title":"I-PHYRE: Interactive Physical Reasoning","created":"2023-12-04","cited_by_count":15,"area":null},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2204.10358","title":"Creative Problem Solving in Artificially Intelligent Agents: A Survey and Framework","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2207.08192","title":"BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2304.00873","title":"Action Pick-up in Dynamic Action Space Reinforcement Learning","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2404.10788","title":"The Path To Autonomous Cyber Defense","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2502.08987","title":"Neural Force Field: Few-shot Learning of Generalized Physical Reasoning","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2508.09021","title":"Attacks and Defenses Against LLM Fingerprinting","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2202.01108","title":"Learning to reason about and to act on physical cascading events","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2205.09738","title":"AIGenC: An AI generalisation model via creativity","created":"2022-05-19","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":"2503.13194","title":"A representational framework for learning and encoding structurally enriched trajectories in complex agent environments","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2607.23771","title":"Training Language Models to Cooperate with Inference-Time Controllers","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}