Online Skill Discovery using Graph-based Clustering
نویسنده
چکیده
We introduce a new online skill discovery method for reinforcement learning in discrete domains. The method is based on the bottleneck principle and identifies skills using a bottom-up hierarchical clustering of the estimated transition graph. In contrast to prior clustering approaches, it can be used incrementally and thus several times during the learning process. Our empirical evaluation shows that “assuming high connectivity in the face of uncertainty” can prevent premature identification of skills. Furthermore, we show that the choice of the linkage criterion is crucial for dealing with non-random sampling policies and stochastic environments.
منابع مشابه
A novel graphical approach to automatic abstraction in reinforcement learning
Recent researches on automatic skill acquisition in reinforcement learning have focused on subgoal discovery methods. Among them, algorithms based on graph partitioning have achieved higher performance. In this paper, we propose a new automatic skill acquisition framework based on graph partitioning approach. The main steps of this framework are identifying subgoals and discovering useful skill...
متن کاملخوشهبندی اسناد مبتنی بر آنتولوژی و رویکرد فازی
Data mining, also known as knowledge discovery in database, is the process to discover unknown knowledge from a large amount of data. Text mining is to apply data mining techniques to extract knowledge from unstructured text. Text clustering is one of important techniques of text mining, which is the unsupervised classification of similar documents into different groups. The most important step...
متن کاملLearning the Structure of Continuous Markov Decision Processes
There is growing interest in artificial, intelligent agents which can operate autonomously for an extended period of time in complex environments and fulfill a variety of different tasks. Such agents will face different problems during their lifetime which may not be foreseeable at the time of their deployment. Thus, the capacity for lifelong learning of new behaviors is an essential prerequisi...
متن کاملFast online graph clustering via Erdös-Rényi mixture
In the context of graph clustering, we consider the problem of estimating simultaneously both the partition of the graph nodes and the parameters of an underlying mixture of affiliation networks. In numerous applications the rapid increase of data size with time makes classical clustering algorithms too slow because of the high computational cost. In such situations online clustering algorithms...
متن کاملEfficient Mining of Graph-Based Data
With the increasing amount of structural data being collected, there arises a need to efficiently mine information from this type of data. The goal of this research is to provide a system that performs data mining on structural data represented as a labeled graph. We demonstrate how the graph-based discovery system Subdue can be used to perform structural pattern discovery and structural hierar...
متن کامل