Markov decision processes (MDPs) have proven to be popular models for decision-theoretic planning, but standard dynamic programming algorithms for solving MDPs rely on explicit, state-based specifications and computations. To alleviate the combinatorial problems associated with such methods, we propose new representational and computational techniques for MDPs that exploit certain types of problem structure. We use dynamic Bayesian networks (with decision trees representing the local families of conditional probability distributions) to represent stochastic actions in an MDP, together with a decision-tree representation of rewards. Based on this representation, we develop versions of standard dynamic programming algorithms that directly manipulate decision-tree representations of policies and value functions. This generally obviates the need for state-by-state computation, aggregating states at the leaves of these trees and requiring computations only for each aggregate state. The key to these algorithms is a decision-theoretic generalization of classic regression analysis, in which we determine the features relevant to predicting expected value. We demonstrate the method empirically on several planning problems,
How seizures start is a major question in epilepsy research. Preictal EEG changes occur in both human patients and animal models, but their underlying mechanisms and relationship with seizure initiation remain unknown. Here we demonstrate the existence, in the hippocampal CA1 region, of a preictal state characterized by the progressive and global increase in neuronal activity associated with a widespread buildup of low-amplitude high-frequency activity (HFA) (Ͼ100 Hz) and reduction in system complexity. HFA is generated by the firing of neurons, mainly pyramidal cells, at much lower frequencies. Individual cycles of HFA are generated by the near-synchronous (within ϳ5 ms) firing of small numbers of pyramidal cells. The presence of HFA in the low-calcium model implicates nonsynaptic synchronization; the presence of very similar HFA in the high-potassium model shows that it does not depend on an absence of synaptic transmission. Immediately before seizure onset, CA1 is in a state of high sensitivity in which weak depolarizing or synchronizing perturbations can trigger seizures. Transition to seizure is characterized by a rapid expansion and fusion of the neuronal populations responsible for HFA, associated with a progressive slowing of HFA, leading to a single, massive, hypersynchronous cluster generating the high-amplitude low-frequency activity of the seizure.
A long-standing goal of AI is to enable robots to plan in the face of uncertain and incomplete information, and to handle task failure intelligently. This paper shows how to achieve this. There are two central ideas. The first idea is to organize the robot's knowledge into three layers: instance knowledge at the bottom, commonsense knowledge above that, and diagnostic knowledge on top. Knowledge in a layer above can be used to modify knowledge in the layer(s) below. The second idea is that the robot should represent not just how its actions change the world, but also what it knows or believes. There are two types of knowledge effects the robot's actions can have: epistemic effects (I believe X because I saw it) and assumptions (I'll assume X to be true). By combining the knowledge layers with the models of knowledge effects, we can simultaneously solve several problems in robotics: (i) task planning and execution under uncertainty; (ii) task planning and execution in open worlds; (iii) explaining task failure; (iv) verifying those explanations. The paper describes how the ideas are implemented in a three-layer architecture on a mobile robot platform. The robot implementation was evaluated in five different experiments on object search, mapping, and room categorization.
This paper shows how state-of-the-art state estimation techniques can be used to provide efficient solutions to the difficult problem of real-time diagnosis in mobile robots. The power of the adopted estimation techniques resides in our ability to combine particle filters with classical algorithms, such as Kalman filters. We demonstrate these techniques in two scenarios: a mobile waiter robot and planetary rovers designed by NASA for Mars exploration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.