J. Gratch and G. DeJong, "A Framework of Simplifications in Learning to Plan," First International Conference on Artificial Intelligence Planning Systems, College Park, MD, 1992, pp. 78--87. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Therapy Plan Generation in Complex Dynamic Environments - Arnold, Jantke (1994) (1 citation) (Correct)
....time restrictions incl. anytime planning ( DB88] RW91] ffl dynamics and unforeseeable effects in plan execution ( Ped87] GL87] Dru89] Fir92] ffl abstraction ( Sac74] Sac77] Ten89] ffl distributed reasoning ( BG88] LB89] Mar93] ffl refinement by learning ( Ham89] GD92] DeJ94] and ffl case based reasoning ( KH92] The pecularities of our target domains introduced above exhibit serious difficulties in specifying postconditions assigned to operators. This key difficulty is rarely considered in the recent literature. There is one relaxation of the standard ....
J. Gratch and Gerald F. DeJong. A framework of simplifications in learning to plan. In AIPS92, pages 78--87. Morgan Kaufmann, 1992.
A Decision-theoretic Approach to Adaptive Problem Solving - Gratch, DeJong (1994) (1 citation) Self-citation (Gratch Dejong) (Correct)
....the utility problem: organizing the search through the space of modifications, estimating utility oftransformations,andgathering statistics. COMPOSERembodiesaparticular set ofcommitments for each of these aspects and thus can be seen as one point in a large space of possible commitments (see also [Gratch92b]) 6.1 APPLICABILITY CONDITIONS COMPOSER embodies numerous restrictions in achieving the goal of efficient learning. As a result, the technique will not apply well to every situation. We can summarize four basic conditions that, if satisfied by an application, should lead to successful results. ....
J. Gratch and G. DeJong, "A Framework of Simplifications in Learning to Plan," First International Conference on Artificial Intelligence Planning Systems, College Park, MD, 1992, pp. 78--87.
An Analysis of Learning to Plan as a Search Problem - Gratch, DeJong (1992) (2 citations) Self-citation (Gratch Dejong) (Correct)
....plan. Like other approaches, it embodies a number of simplifications to overcome the complexities of learning. These simplifications introduce tradeoffs between learning efficiency and effectiveness. In this paper we relate COMPOSER to our general framework of simplifications for learning to plan [Gratch92a]. This discussion illustrates how such a framework may be used to analyzea particular approach, highlighting the learning system s strengths and weaknesses. 1 INTRODUCTION In machine learning there is considerable interest in techniqueswhichimproveplanning ability. Investigation in this area has ....
....of these approaches are not wellunderstood. This is highlighted by demonstrations where learning degrades planning performance [Etzioni90b, Gratch91a, Minton85, Subramanian90] In this paper we relate a particular learning system to our general framework for learning to plan described in [Gratch92a] The framework provides a unifying perspective where seemingly different approaches are related through their use of common simplifying assumptions. We review the framework (Section 3) and then turn to describing the COMPOSER [Gratch92b] technique from this new perspective (Section 4) The ....
[Article contains additional citation context not shown here]
J. Gratch and G. DeJong, "A Framework of Simplifications in Learning to Plan," First International Conference on Artificial Intelligence Planning Systems, College Park, MD, 1992.
COMPOSER: A Probabilistic Solution to the. . . - Gratch, DeJong (1992) Self-citation (Gratch Dejong) (Correct)
No context found.
J. Gratch and G. DeJong, "A Framework of Simplifications in Learning to Plan," First International Conference on Artificial Intelligence Planning Systems, College Park, MD, 1992.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC