Results 1 
6 of
6
Merging Separately Generated Plans with Restricted Interactions
, 1992
"... Generating action sequences to achieve a set of goals is a computationally difficult task. When multiple goals are present, the problem is even worse. Although many solutions to this problem have been discussed in the literature, practical solutions focus on the use of restricted mechanisms for plan ..."
Abstract

Cited by 27 (8 self)
 Add to MetaCart
Generating action sequences to achieve a set of goals is a computationally difficult task. When multiple goals are present, the problem is even worse. Although many solutions to this problem have been discussed in the literature, practical solutions focus on the use of restricted mechanisms for planning or the application of domain dependent heuristics for providing rapid solutions (i.e. domaindependent planning). One previously proposed technique for handling multiple goals efficiently is to design a planner or even a set of planners (usually domaindependent) that can be used to generate separate plans for each goal. The outputs are typically either restricted to be independent and then concatenated into a single global plan, or else they are merged together using complex heuristic techniques. In this paper we explore a set of limitations, less restrictive than the assumption of independence, that still allow for the efficient merging of separate plans using straightforward algorith...
Pointbased incremental pruning heuristic for solving finitehorizon DECPOMDPs
 In Proc. of the Eighth Int. Joint Conf. on Autonomous Agents and Multiagent Systems
, 2009
"... Recent scaling up of decentralized partially observable Markov decision process (DECPOMDP) solvers towards realistic applications is mainly due to approximate methods. Of this family, MEMORY BOUNDED DYNAMIC PROGRAMMING (MBDP), which combines in a suitable manner topdown heuristics and bottomup va ..."
Abstract

Cited by 16 (5 self)
 Add to MetaCart
Recent scaling up of decentralized partially observable Markov decision process (DECPOMDP) solvers towards realistic applications is mainly due to approximate methods. Of this family, MEMORY BOUNDED DYNAMIC PROGRAMMING (MBDP), which combines in a suitable manner topdown heuristics and bottomup value function updates, can solve DECPOMDPs with large horizons. The performances of MBDP, can be, however, drastically improved by avoiding the systematic generation and evaluation of all possible policies which result from the exhaustive backup. To achieve that, we suggest a heuristic search method, namely POINT BASED INCREMENTAL PRUNING (PBIP), which is able to distinguish policies with different heuristic estimates. Taking this insight into account, PBIP searches only among the most promising policies, finds those useful, and prunes dominated ones. Doing so permits us to reduce clearly the amount of computation required by the exhaustive backup. The computation experiment shows that PBIP solves DECPOMDP benchmarks up to 800 times faster than the current best approximate algorithms, while providing solutions with higher values.
Global Search Methods For Solving Nonlinear Optimization Problems
, 1997
"... ... these new methods, we develop a prototype, called Novel (Nonlinear Optimization Via External Lead), that solves nonlinear constrained and unconstrained problems in a unified framework. We show experimental results in applying Novel to solve nonlinear optimization problems, including (a) the lear ..."
Abstract

Cited by 15 (1 self)
 Add to MetaCart
... these new methods, we develop a prototype, called Novel (Nonlinear Optimization Via External Lead), that solves nonlinear constrained and unconstrained problems in a unified framework. We show experimental results in applying Novel to solve nonlinear optimization problems, including (a) the learning of feedforward neural networks, (b) the design of quadraturemirrorfilter digital filter banks, (c) the satisfiability problem, (d) the maximum satisfiability problem, and (e) the design of multiplierless quadraturemirrorfilter digital filter banks. Our method achieves better solutions than existing methods, or achieves solutions of the same quality but at a lower cost.
A Scalable Parallel Tree Search Library
 2nd Workshop on Solving Irregular Problems on Distributed Memory Machines
, 1996
"... This paper reports design and implementation experiences with the portable and reusable library PIGSeL for parallel tree search. It is discussed how efficiency, flexibility and usability of the library can be reconciled. Two sample applications demonstrate its effectiveness for the case of parallel ..."
Abstract

Cited by 5 (4 self)
 Add to MetaCart
This paper reports design and implementation experiences with the portable and reusable library PIGSeL for parallel tree search. It is discussed how efficiency, flexibility and usability of the library can be reconciled. Two sample applications demonstrate its effectiveness for the case of parallel depthfirst search. On a mesh of 1024 Transputers near optimal speedup even for small instances of the Golomb ruler problem is achieved. The 0/1 knapsack problem is more challenging but the library achieves good speedups for quite irregular problem instances. From the algorithmic point of view, this is due to the random polling load balancing algorithm which turns out to perform well even on highdiameter networks, and also due to a fast initialization scheme, a bottleneck free implementation of the branchandbound heuristics and an adaption of the tree based doublecounting termination detection algorithm. 1 Introduction Many applications are based on the traversal of large implicitly defi...
A Concept Formation Based Algorithmic Model for Skill Acquisition
 Proc. First European Workshop on Cognitive Modelling
, 1996
"... We present an algorithmic model for acquisition of cognitive skills that is based on machine learning and problem solving algorithms. The principle is to use a problem solving approach for new problems that are not covered by the routine knowledge obtained from generalizing previous samples, and to ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
We present an algorithmic model for acquisition of cognitive skills that is based on machine learning and problem solving algorithms. The principle is to use a problem solving approach for new problems that are not covered by the routine knowledge obtained from generalizing previous samples, and to use a machine learning algorithm to generalize these samples to an abstraction of the state space. We show the admissibility of our approach, discuss complexity results and present empirical results for Rubik's cube and a maze problem. 1 Introduction The problem of skill acquisition has been approached from various perspectives, ranging from a psychological, e.g. [And93] to a machine learning point of view, e.g. [MC68, BSA83]. While most work on skill acquisition in machine learning focuses on control skills, e.g. [ML892, DBS93], this paper mainly deals with cognitive skills. Known models for cognitive skills include Soar [LNR87] and ActR [And93]. In contrast to Soar, which is a mainly imp...
Parallel and Distributed BranchandBound/A* Algorithms
, 1994
"... In this report, we propose new concurrent data structures and load balancing strategies for BranchandBound (B&B)/A* algorithms in two models of parallel programming : shared and distributed memory. For the shared memory model (SMM), we present a general methodology which allows concurrent manipul ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
In this report, we propose new concurrent data structures and load balancing strategies for BranchandBound (B&B)/A* algorithms in two models of parallel programming : shared and distributed memory. For the shared memory model (SMM), we present a general methodology which allows concurrent manipulations for most tree data structures, and show its usefulness for implementation on multiprocessors with global shared memory. Some priority queues which are suited for basic operations performed by B&B algorithms are described : the Skewheaps, the funnels and the Splaytrees. We also detail a specific data structure, called treap and designed for A* algorithm. These data structures are implemented on a parallel machine with shared memory : KSR1. For the distributed memory model (DMM), we show that the use of partial cost in the B&B algorithms is not enough to balance nodes between the local queues. Thus, we introduce another notion of priority, called potentiality, between nodes that take...