跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 10 天前AI 評分47

長時程智能體中的決策模型:行動者、評判者還是教師?

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

AI 導讀

研究發現,表現不佳的決策模型仍可透過評判完整行動軌跡,有效教導強化學習策略。JEV以GRPO訓練Qwen2.5-1.5B策略後,ALFWorld成功率由72.8%升至82.9%,WebShop則由56.8%升至71.4%。逐一判斷每個行動是否有幫助,能區分有用和無用的行動。

正文

Published on Nov 12

Authors:

,

,

,

,

,

,

,

,

Abstract

A decision model that acts poorly can still teach reinforcement learning policies effectively by judging complete action trajectories, improving success on ALFWorld and WebShop.

Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studied them mainly as actors, judging their usefulness by how well they act. We ask whether a decision model that acts poorly can still teach well. We compare three decision models and three general LLMs as actors and judges on ALFWorld, and use JEV as a teacher on ALFWorld and WebShop. As actors, all six models are pulled away from a subgoal that must come first by an easier one. As judges that see the whole trajectory, the same models credit the steps toward that subgoal, and asking whether each action helped, rather than whether the task will succeed, separates useful from useless actions. As a teacher, JEV raises a Qwen2.5-1.5B policy over GRPO from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop. These results suggest that a poor actor can still teach well, because judging an action after the episode ends reveals the consequences that acting must anticipate. Code is available at https://github.com/ZJU-REAL/decision-agents.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.17167

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.17167 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.17167 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.17167 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co