arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1206.6484cs.LGcs.AIstat.ML
收藏

部分可观测环境模型参数的学徒学习

Apprenticeship Learning for Model Parameters of Partially Observable Environments

Institute of Industrial Science, the University of Tokyo(东京大学生产技术研究所);Honda Research Institute Japan Co., Ltd.(日本本田技术研究所株式会社)

Takaki Makino, Johane Takeuchi

摘要:

我们认为学徒制学习,即,当环境模型不确定时,使代理通过观察专家在部分可观察环境中演示任务来学习任务。此设置在难以对环境进行显式建模的应用程序(如对话系统)中非常有用。我们表明,我们可以提取信息的环境模型推断动作选择过程背后的演示,假设专家选择最佳行动的基础上的知识的目标环境的真实模型。提出的算法可以实现更准确的估计POMDP参数和更好的政策,从一个简短的演示,相比,只从环境的反应学习的方法。

英文摘要:

We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialogue system. We show that we can extract information about the environment model by inferring action selection process behind the demonstration, under the assumption that the expert is choosing optimal actions based on knowledge of the true model of the target environment. Proposed algorithms can achieve more accurate estimates of POMDP parameters and better policies from a short demonstration, compared to methods that learns only from the reaction from the environment.

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。

↑