arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.17543cs.LGcs.AIcs.CL
收藏

训练一个具有通用好奇心的智能体

Training a Generally Curious Agent

North Carolina State University(北卡罗来纳州立大学)

Fahim Tajwar, Yiding Jiang, Abitha Thankaraj, Sumaita Sadia Rahman, J Zico Kolter, Jeff Schneider, Ruslan Salakhutdinov

AI总结:

提出微调方法Paprika,通过在多样化策略的合成交互数据上训练,使语言模型基于环境反馈进行上下文探索,无需梯度更新即可将决策能力迁移至未见任务,并利用课程学习策略提升样本效率。

摘要:

高效探索对于与环境交互的智能系统至关重要,但现有的语言模型在需要策略性信息收集的场景中往往表现不佳。本文提出了Paprika,这是一种微调方法,使语言模型能够发展出不局限于特定环境的通用决策能力。通过在不同任务需要多样化策略的合成交互数据上进行训练,Paprika教会模型在上下文中基于环境反馈探索并调整其行为以适应新任务,而无需更多的梯度更新。实验结果表明,使用Paprika微调的模型能够将学到的决策能力有效迁移到完全未见的任务中,且无需额外训练。与传统的训练不同,该方法的主要瓶颈在于采样有用的交互数据,而非模型更新。为了提高样本效率,我们提出了一种课程学习策略,优先从具有高学习潜力的任务中采样轨迹。这些结果为AI系统能够自主解决需要与外部世界交互的新型序列决策问题指明了一条有前景的路径。

英文摘要:

Efficient exploration is essential for intelligent systems interacting with their environment, but existing language models often fall short in scenarios that require strategic information gathering. In this paper, we present Paprika, a fine-tuning approach that enables language models to develop general decision-making capabilities that are not confined to particular environments. By training on synthetic interaction data from different tasks that require diverse strategies, Paprika teaches models to explore and adapt their behavior on a new task based on environment feedback in-context without more gradient updates. Experimental results show that models fine-tuned with Paprika can effectively transfer their learned decision-making capabilities to entirely unseen tasks without additional training. Unlike traditional training, our approach's primary bottleneck lies in sampling useful interaction data instead of model updates. To improve sample efficiency, we propose a curriculum learning strategy that prioritizes sampling trajectories from tasks with high learning potential. These results suggest a promising path towards AI systems that can autonomously solve novel sequential decision-making problems that require interactions with the external world.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑