Layered Learning

By Peter Stone, Manuela M. Veloso. 2000

174 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Deep Hierarchical Approach to Lifelong Learning in Minecraft (2016, background): “Many of the tasks that are encountered by an agent in a lifelong learning setting can be naturally decomposed into skill hierarchies (Stone et al. 2000; Stone, Sutton, and Kuhlmann 2005; Bai, Wu, and Chen 2015).”
Many-Layered Learning (2002, background): “For example, Stone & Veloso (2000) have explored many-layered learning in the domain of robotic soccer, having observed that the larger learning tasks were intractable with standard (Type-1) methods.”
An Introduction to Deep Reinforcement Learning (2018, unknown): “, 2016) and decomposing learning into skill hierarchies (Stone and Veloso, 2000; Tessler et al., 2017).”
Learning from observation using primitives (2001, background): “Providing robots with primitives greatly aids in the programming of the robot because it limits the possible state-action pairs that need to be considered and provides a higher-level description of the task that needs to be performed [120].”
Character Recognition Systems: A Guide for Students and Practitioners (2007, background): “There is a long way, not yet traveled, toward applying and advancing many computer science techniques, such as hierarchical genetic programing [8], layered learning [106], Adaptive representations of learning [95] and, of course, automatically defined functions [61] to the problem of feature creatio”
Evolving Soccer Keepaway Players Through Task Decomposition (2005, background): “3 This section is adapted from (Stone and Veloso, 2000).”
Introduction to the Special Issue on Meta-Learning (2004, background): “The idea is somewhat related to layered learning (Stone & Veloso, 2000; Utgoff & Stracuzzi, 2003), except tasks need not build on top of each other but simply interact with each other.”
Cooperation and communication in multiagent deep reinforcement learning (2016, background): “Layered learning has been effective in both 2D and 3D RoboCup simulated soccer domains (MacAlpine et al., 2015b; Stone and Veloso, 2000).”
Evolving Keepaway Soccer Players through Task Decomposition (2003, background): “One approach to training the components of a task decomposition is layered learning, a bottom-up paradigm in which low-level behaviors are learned prior to high-level ones [16].”