按年被提到
20212021 · 1 次2026
强化学习与智能体›大模型智能体·arXiv:2101.09571 · cs.AI

BF++: a language for general-purpose program synthesis

Vadim Liventsev, Aki Härmä, Milan Petković · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-12-05 · 最近 2022-02-08
2不同的人
2活跃月份
2讨论串
3被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models, where it is often difficult to incorporate expert knowledge into the models or let experts review and validate the learned decision mechanisms. Knowledge-insertion and model review are important requirements in many applications involving human health and safety. One way to bridge the gap between data and knowledge driven systems is program synthesis: replacing a neural network that outputs decisions with a symbolic program generated by a neural network or by means of genetic programming. We propose a new programming language, BF++, designed specifically for automatic programming of agents in a Partially Observable Markov Decision Process (POMDP) setting and apply neural program synthesis to solve standard OpenAI Gym benchmarks.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ahgamut · 2022-02

“> I would actually be more impressed if it understood enough about programs to be able to mimic higher-level structure without just memorizing text. Agreed. > Why do you think Python isn't good for comparing program structure? From recent experience I prefer control flow analysis, or something that results in a graph structure. As you said, that's hard…”

AlphaCode as a dog speaking mediocre English原评论 ↗
被提交为 story · 1 次