Relational Knowledge with Predictive State Representations
نویسندگان
چکیده
Most work on Predictive Representations of State (PSRs) has focused on learning and planning in unstructured domains (for example, those represented by flat POMDPs). This paper extends PSRs to represent relational knowledge about domains, so that they can use policies that generalize across different tasks, capture knowledge that ignores irrelevant attributes of objects, and represent policies in a way that is independent of the size of the state space. Using a blocks world domain, we show how generalized predictions about the future can compactly capture relations between objects, which in turn can be used to naturally specify relational-style options and policies. Because our representation is expressed solely in terms of actions and observations, it has extensive semantics which are statistics about observable quantities.
منابع مشابه
Learning by observation using Qualitative Spatial Relations
We present an approach to the problem of learning by observation in spatially-situated tasks, whereby an agent learns to imitate the behaviour of an observed expert with no interaction and limited observations. The form of knowledge representation used for these observations is crucial, and we apply Qualitative Spatial-Relational representations to compress continuous, metric state-spaces into ...
متن کاملRelational Reinforcement Learning in Infinite Mario
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning beh...
متن کاملLearning Causal Models of Relational Domains
Methods for discovering causal knowledge from observational data have been a persistent topic of AI research for several decades. Essentially all of this work focuses on knowledge representations for propositional domains. In this paper, we present several key algorithmic and theoretical innovations that extend causal discovery to relational domains. We provide strong evidence that effective le...
متن کاملLearning in Rich Representations: Inductive Logic Programming and Computational Scientific Discovery
• Encourage more research on learning in rich representations, such as relational representations and differential equations, which can be used for modeling a variety of real world problems. Inductive logic programming (ILP) is concerned with learning from data and domain knowledge in relational representations. ILP started off by addressing the task of learning logic programs from examples and...
متن کاملKBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
We present KBLRN, a novel framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. We discuss the advantages of each of the three feature types and the benefits of their combination. To the best of our knowledge, KBLRN is the first machine learning approach that learns representations of knowledge bases by integrating latent, relationa...
متن کامل