按年被提到
20232023 · 4 次2026
强化学习与智能体›深度强化学习与世界模型·arXiv:2310.12931 · cs.RO

Eureka: Human-Level Reward Design via Coding Large Language Models

Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, Anima Anandkumar · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2023-10-21 · 最近 2026-05-07
4不同的人
2活跃月份
5讨论串
139被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open problem. We bridge this fundamental gap and present Eureka, a human-level reward design algorithm powered by LLMs. Eureka exploits the remarkable zero-shot generation, code-writing, and in-context improvement capabilities of state-of-the-art LLMs, such as GPT-4, to perform evolutionary optimization over reward code. The resulting rewards can then be used to acquire complex skills via reinforcement learning. Without any task-specific prompting or pre-defined reward templates, Eureka generates reward functions that outperform expert human-engineered rewards. In a diverse suite of 29 open-source RL environments that include 10 distinct robot morphologies, Eureka outperforms human experts on 83% of the tasks, leading to an average normalized improvement of 52%. The generality of Eureka also enables a new gradient-free in-context learning approach to reinforcement learning from human feedback (RLHF), readily incorporating human inputs to improve the quality and the safety of the generated rewards without model updating. Finally, using Eureka rewards in a curriculum learning setting, we demonstrate for the first time, a simulated Shadow Hand capable of performing pen spinning tricks, adeptly manipulating a pen in circles at rapid speed.

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og_kalu · 2023-10

“From the paper, https://arxiv.org/abs/2310.12931 "In addition, by examining the average correlation by task (App. E), we observe that the harder the task is, the less correlated the EUREKA rewards. We hypothesize that human rewards are less likely to be near optimal for difficult tasks, leaving more room for EUREKA rewards to be different and better. In …”

Eureka! Nvidia Research Breakthrough Puts New Spin on Robot Learning原评论 ↗
评论stalfie · 2026-05

“Well, if the evaluation infrastructure is something humans could have had access to before, and that the agents key "skill" is just that it's a more patient and scalable worker, I would still argue that this "comes from the agent". Humans get bored, inpatient, or run out of time, and so often give up in what they perceive to be a decent "local minima". E…”

AlphaEvolve: Gemini-powered coding agent scaling impact across fields原评论 ↗
被提交为 story · 3 次