Learning in embedded systems

By Leslie Pack Kaelbling. 1993

How researchers see this paper

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

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, background): “Using upper confidence bounds (Kaelbling, 1990) to direct exploration into regions with potentially high rewards, grasping can be learned efficiently (Kroemer et al., 2010).”
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning (2020, background): “These systems must adapt online to maximize their cumulative rewards [30, 31].”
Bandit Algorithms (2020, background): “A notable example of the former type is ‘prospect theory’ [Kahneman and Tversky, 1979], which models how people handle probabilities (especially small ones) and earned Daniel Khaneman a Nobel prize (after the death of his long-time collaborator, Amos Tversky). Further descriptive theories concerned ”
Reinforcement Learning: An Introduction (1998, methodology): “As we outlined in Chapter 1, the idea of TD learning has its early roots in animal learning psychology and artificial intelligence, most notably the work of Samuel (1959) and Klopf (1972). Samuel’s work is described as a case study in Section 15.”
Variable Resolution Discretization in Optimal Control (2002, methodology): “Local value-based splitting is an efficient, model-based, relative of the Q-learning-based tree splitting criteria used, for example, by Chapman and Kaelbling (1991); Simons et al. (1982) and McCallum (1995).”
Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement (1997, background): “To measure the cost of a single program, we simply count the total number of forward steps and rotations during program execution (this number is of the order of total computation time).”
Reinforcement Learning and Markov Decision Processes (2012, methodology): “The interval estimation (IE) method Kaelbling (1993) is an example of this kind of methods.”
Active Policy Learning for Robot Planning and Exploration under Uncertainty (2008, background): “In [16], the problem is treated in the framework of exploration/exploitation with bandits.”
Locally Weighted Learning for Control (1997, methodology): “To resolve this dilemma, a number of useful exploration heuristics can be used, all based on the idea that it is worth exploring only where there is little confidence in the empirical model (Sutton 1990; Kaelbling 1993; Moore and Atkeson 1993; Cohn et al. 1995).”
Planning, Learning and Coordination in Multiagent Decision Processes (1996, background): “However, considerations of optimal exploration strategies and optimal learning have been explored, especially in relation to k-armed bandit problems [27, 28].”
Robot shaping: developing situated agents through learning (1992, methodology): “dissertation Kaelbling has been using reinforcement learning to let a robot – called Spanky – learn to approach a light source and to avoid obstacles (Kaelbling, 1990; but see also Kaelbling, 1991).”
Learning to Act Using Real-Time Dynamic Programming (1995, background): “For example, Chapman and Kaelbling [ 151 and Tan [76] adapt decisiontree methods, and Mahadevan and Connell [49] use a statistical clustering method.”