{"total":10,"rows":[{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2303.06018","title":"Hierarchical Neural Program Synthesis","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2405.05431","title":"Searching for Programmatic Policies in Semantic Spaces","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2410.12166","title":"Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2503.08738","title":"Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2605.03413","title":"Learning to Theorize the World from Observation","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2608.03461","title":"Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}