%0 Journal Article %T Using Vector Representation of Propositions and Actions for STRIPS Action Model Learning<br>Using Vector Representation of Propositions and Actions for STRIPS Action Model Learning %A Wei Gao %A Dunbo Cai %J 北京理工大学学报（自然科学中文版) %D 2018 %R 10.15918/j.jbit1004-0579.18072 %X Action model learning has become a hot topic in knowledge engineering for automated planning. A key problem for learning action models is to analyze state changes before and after action executions from observed "plan traces". To support such an analysis, a new approach is proposed to partition propositions of plan traces into states. First, vector representations of propositions and actions are obtained by training a neural network called Skip-Gram borrowed from the area of natural language processing (NLP). Then, a type of semantic distance among propositions and actions is defined based on their similarity measures in the vector space. Finally, k-means and k-nearest neighbor (kNN) algorithms are exploited to map propositions to states. This approach is called state partition by word vector (SPWV), which is implemented on top of a recent action model learning framework by Rao et al. Experimental results on the benchmark domains show that SPWV leads to a lower error rate of the learnt action model, compared to the probability based approach for state partition that was developed by Rao et al.<br>Action model learning has become a hot topic in knowledge engineering for automated planning. A key problem for learning action models is to analyze state changes before and after action executions from observed "plan traces". To support such an analysis, a new approach is proposed to partition propositions of plan traces into states. First, vector representations of propositions and actions are obtained by training a neural network called Skip-Gram borrowed from the area of natural language processing (NLP). Then, a type of semantic distance among propositions and actions is defined based on their similarity measures in the vector space. Finally, k-means and k-nearest neighbor (kNN) algorithms are exploited to map propositions to states. This approach is called state partition by word vector (SPWV), which is implemented on top of a recent action model learning framework by Rao et al. Experimental results on the benchmark domains show that SPWV leads to a lower error rate of the learnt action model, compared to the probability based approach for state partition that was developed by Rao et al. %K automated planning action model learning vector representation of propositions< %K br> %K automated planning action model learning vector representation of propositions %U http://journal.bit.edu.cn/yw/bjlgyw/ch/reader/view_abstract.aspx?file_no=20180402&flag=1