Decision problem

About: Decision problem is a research topic. Over the lifetime, 6917 publications have been published within this topic receiving 170370 citations.

Maximum entropy inverse reinforcement learning

Abstract: Recent research has shown the benefit of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces learning to the problem of recovering a utility function that makes the behavior induced by a near-optimal policy closely mimic demonstrated behavior. In this work, we develop a probabilistic approach based on the principle of maximum entropy. Our approach provides a well-defined, globally normalized distribution over decision sequences, while providing the same performance guarantees as existing methods. We develop our technique in the context of modeling real-world navigation and driving behaviors where collected data is inherently noisy and imperfect. Our probabilistic approach enables modeling of route preferences as well as a powerful new approach to inferring destinations and routes based on partial trajectories.

A decision method for elementary algebra and geometry

Abstract: By a decision method for a class K of sentence (or other expressions) is meant a method by means of which, given any sentence θ, one can always decide in a finite number of steps whether θ is in K; by a decision problem for a class K we mean the problem of finding a decision method for K. A decision method must be like a recipe, which tells one what to do at each steps so that no intelligence is required to follow it; and the method can be applied by anyone so long as he is able to read and follow directions.

Adaptive Strategy Selection in Decision Making.

Abstract: : The authors examine the role of effort and accuracy in the adaptive use of decision processes. A computer simulation study that used the concept of elementary information processes identified heuristic choice strategies which approximate the accuracy of normative procedures while requiring substantially less effort. However, no single heuristic did well across all task and context conditions. Of particular interest was the finding that under time constraints, several heuristics were clearly more accurate than a normative procedure. Two process tracing studies showed a significant degree of correspondence between the efficient strategies for a given decision problem identified by the simulation and actual decision behavior. People were highly adaptive to changes in the nature of the alternatives available to them and to the presence of time pressure. (Author)

Online Passive-Aggressive Algorithms

Abstract: We present a family of margin based online learning algorithms for various prediction tasks. In particular we derive and analyze algorithms for binary and multiclass categorization, regression, uniclass prediction and sequence prediction. The update steps of our different algorithms are all based on analytical solutions to simple constrained optimization problems. This unified view allows us to prove worst-case loss bounds for the different algorithms and for the various decision problems based on a single lemma. Our bounds on the cumulative loss of the algorithms are relative to the smallest loss that can be attained by any fixed hypothesis, and as such are applicable to both realizable and unrealizable settings. We demonstrate some of the merits of the proposed algorithms in a series of experiments with synthetic and real data sets.

Multicriteria Methodology for Decision Aiding

Abstract: Reader's Guide. Foreword to the English-Language Edition. Introductory: How to Aid Whom with What Types of Decision. 1. Decision Problems and Processes. 2. Decision Aiding: Major Actors and the Role of Models. 3. Reference Examples. 4. Phases and Options of an Approach to Decision Aiding (General Ideas of the Methodology). Level I: How to Determine What is Possible and in What Terms to Formulate a Problem. 5. Actions and Decision Aiding. 6. Problematics as Guides in Decision Aiding. Level II: How to Determine Preferences and on What Bases. 7. Preference, Indifference, Incomparability: Binary Relations and Basic Structures. 8. Comparing Actions and Modeling Consequences. 9. Comparing Actions and Developing Criteria. Levels III and IV: How to Proceed from Multiple Criteria to Comprehensive Preferences and Develop Recommendations. 10. Coherent Criterion Family and Decision Aiding in the Description Problematic. 11. Modeling Comprehensive Preferences: Three Operational Approaches for Progressing Beyond the Description Problematic. 12. Specific Difficulties in Choice, Sorting, and Ranking Problematics. Bibliography. Index.