Learning to Represent State with Perceptual Schemata
The real world is large and complex. It is filled with many objects besides those defined by a task and objects can move with their own interesting dynamics. How should an agent learn to represent state to support efficient learning and generalization in such an environment? In this work, we present a novel memory architecture, Perceptual Schemata, for learning and zero-shot generalization in environments that have many, potentially moving objects. Perceptual Schemata represents state using a combination of schema modules that each learn to attend to and maintain stateful representations of different subspaces of a spatio-temporal tensor describing the agent’s observations. We present empirical results that Perceptual Schemata enables a state representation that can maintain multiple objects observed in sequence with independent dynamics while an LSTM cannot. We additionally show that Perceptual Schemata can generalize more gracefully to larger environments with more distractor objects, while an LSTM quickly overfits to the training tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Zero-shot GeneralizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Induce, Edit, Retrieve:Language Grounded Multimodal Schema for Instructional Video Retrieval
Schemata are structured representations of complex tasks that can aid artificial intelligence by allowing models to break down complex tasks into intermediate steps. We propose a novel system that induces schemata from w…
RetrievalVideo RetrievalDecidability and Undecidability Results for Propositional Schemata
We define a logic of propositional formula schemata adding to the syntax of propositional logic indexed propositions and iterated connectives ranging over intervals parameterized by arithmetic variables. The satisfiabili…
A New Representation for Span-based CCG Parsing
This paper proposes a new representation for CCG derivations. CCG derivations are represented as trees whose nodes are labeled with categories strictly restricted by CCG rule schemata. This characteristic is not suitable…
Interoperability and Customisation of Annotation Schemata in Argo
The process of annotating text corpora involves establishing annotation schemata which define the scope and depth of an annotation task at hand. We demonstrate this activity in Argo, a Web-based workbench for the analysi…
ManagementMachine learning as a model for cultural learning: Teaching an algorithm what it means to be fat
As we navigate our cultural environment, we learn cultural biases, like those around gender, social class, health, and body weight. It is unclear, however, exactly how public culture becomes private culture. In this pape…
ArticlesCultural Vocal Bursts Intensity PredictionLanguage ModellingNavigate+1