paper-with-me

Papers

InnateCoder: Learning Programmatic Options with Foundation Models

2025-05-18 · Rubens O. Moraes, Quazi Asif Sadmine, Hendrik Baier, Levi H. S. Lelis

Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to learn even the most obvious skills required to solve a problem. In this paper, we present InnateCoder, a system that leverages human knowledge encoded in foundation models to provide programmatic policies that encode "innate skills" in the form of temporally extended actions, or options. In contrast to existing approaches to learning options, InnateCoder learns them from the general human knowledge encoded in foundation models in a zero-shot setting, and not from the knowledge the agent gains by interacting with the environment. Then, InnateCoder searches for a programmatic policy by combining the programs encoding these options into larger and more complex programs. We hypothesized that InnateCoder's way of learning and using options could improve the sampling efficiency of current methods for learning programmatic policies. Empirical results in MicroRTS and Karel the Robot support our hypothesis, since they show that InnateCoder is more sample efficient than versions of the system that do not use options or learn them from experience.

📄 PDF Abstract BibTeX arXiv:2505.12508

Code (1)

rubensolv/InnateCoder 공식 구현 pytorch

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

CoMa: Contextual Massing Generation with Vision-Language Models

2026-01-13 · Evgenii Maslov, Valentin Khrulkov, Anastasia Volkova, Anton Gusarov 외 arxiv

The conceptual design phase in architecture and urban planning, particularly building massing, is complex and heavily reliant on designer intuition and manual effort. To address this, we propose an automated framework fo…

TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning

2026-03-08 · Mingyue Cheng, Shuo Yu, Chuang Jiang, Xiaoyu Tao 외 arxiv

Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow a…

Reinforcement Learning

Programmatic Reinforcement Learning: Navigating Gridworlds

2024-02-18 · Guruprerana Shabadi, Nathanaël Fijalkow, Théo Matricon

The field of reinforcement learning (RL) is concerned with algorithms for learning optimal policies in unknown stochastic environments. Programmatic RL studies representations of policies as programs, meaning involving h…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces

2024-10-16 · Tales H. Carvalho, Kenneth Tjhia, Levi H. S. Lelis

Recent works have introduced LEAPS and HPRL, systems that learn latent spaces of domain-specific languages, which are used to define programmatic policies for partially observable Markov decision processes (POMDPs). Thes…

NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines

2026-02-13 · Guoan Wang, Shihao Yang, Jun-En Ding, Feng Liu arxiv

Although foundation models have demonstrated remarkable success in general domains, the application of these models to electroencephalography (EEG) analysis is constrained by substantial data requirements and high parame…