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 2306.09082cs.AI
收藏

通过在嵌入的演示数据集中搜索实现行为克隆

Behavioral Cloning via Search in Embedded Demonstration Dataset

University of Eastern Finland(东芬兰大学);Bielefeld University(比勒费尔德大学)

Federico Malato, Florian Leopold, Ville Hautamaki, Andrew Melnik

AI总结:

针对行为克隆的学习与策略适配问题,提出在隐空间索引演示数据集、通过搜索相似经验复制行为的方法,在Minecraft场景下性能与训练模型相当,支持零样本任务适配。

摘要:

行为克隆利用演示数据集来学习行为策略。为解决各类学习与策略适配问题,我们提出利用隐空间对演示数据集建立索引,即时调取相似的相关经验,并从这些情境中复制行为。智能体可执行所选相似情境对应的动作,直到智能体当前情境的表征与所选经验的表征在隐空间中出现差异。由此,我们将控制问题建模为在专家演示数据集上的搜索问题。我们在Video PreTraining(视频预训练)模型的隐表征下,基于BASALT MineRL数据集对所提方法进行测试,并将模型与前沿的Minecraft智能体对比。我们的方法能有效检索到有意义的演示,在多种场景下的Minecraft环境中展现出类人的智能体行为。实验结果表明,这种基于搜索的方法性能与训练后的模型相当,同时可通过更换演示示例实现零样本任务适配。

英文摘要:

Behavioural cloning uses a dataset of demonstrations to learn a behavioural policy. To overcome various learning and policy adaptation problems, we propose to use latent space to index a demonstration dataset, instantly access similar relevant experiences, and copy behavior from these situations. Actions from a selected similar situation can be performed by the agent until representations of the agent's current situation and the selected experience diverge in the latent space. Thus, we formulate our control problem as a search problem over a dataset of experts' demonstrations. We test our approach on BASALT MineRL-dataset in the latent representation of a Video PreTraining model. We compare our model to state-of-the-art Minecraft agents. Our approach can effectively recover meaningful demonstrations and show human-like behavior of an agent in the Minecraft environment in a wide variety of scenarios. Experimental results reveal that performance of our search-based approach is comparable to trained models, while allowing zero-shot task adaptation by changing the demonstration examples.

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。

↑