A Bayesian model of plan recognition

Charniak, Eugene; Goldman, Robert P.

doi:10.1016/0004-3702(93)90060-o

Cited by 303 publications

(214 citation statements)

References 3 publications

Supporting

Mentioning

203

Contrasting

Unclassified

Order By: Relevance

“…The plays are given in terms for goals for the agents and limited temporal constraints between actions. Further, similar to Charniak and Goldman [1], they use Bayesian style networks to incorporate observed information.…”

Section: Discussionmentioning

confidence: 99%

Recognizing Probabilistic Opponent Movement Models

Riley

Veloso

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In multiagent adversarial domains, team agents should adapt to the environment and opponent. We introduce a model representation as part of a planning process for a simulated soccer domain. The planning is centralized, but the plans are executed in a multi-agent environment, with teammate and opponent agents. Further, we present a recognition algorithm where the model which most closely matches the behavior of the opponents can be selected from few observations of the opponent. Empirical results are presented to verify that important information is maintained through the abstraction the models provide.

show abstract

Section: Discussionmentioning

confidence: 99%

Recognizing Probabilistic Opponent Movement Models

Riley

Veloso

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Unlike Pynadath and Wellman (1995), Huber et al (1994), and Charniak and Goldman (1993), he does not show how BNs can be used on-line to perform plan recognition inferences in specific cases. Instead, he offers a theoretical analysis, in terms of Bayesian inference, of several general, nonprobabilistic plan recognition heuristics that have been proposed by previous researchers.…”

Section: Off-line Bayesian Analysis For Plan Recognitionmentioning

confidence: 91%

“…Each of these BNs would be specialized in the recognition of ways in which the user might pursue a particular high-level goal. This top-down approach is in some respects opposed to that of Charniak and Goldman (1993), which will be examined in the next subsection, in which plan recognition BNs are generated bottom-up on the basis of information about an agent's actions.…”

Section: Reusing Plan Generation Knowledge For Plan Recognitionmentioning

confidence: 99%

“…Yet only one of the two links can be included, because a BN cannot include cycles. Charniak and Goldman (1993) and (more briefly) Charniak and Goldman (1991) present an impassioned argument for the use of BNs for plan recognition; they argue, in particular, for the superiority of their approach to the DST-based approach of Carberry (1990; cf. Section 3.2 below).…”

Section: Reusing Plan Generation Knowledge For Plan Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Numerical uncertainty management in user and student modeling: An overview of systems and issues

Jameson¹

1996

User Model User-Adap Inter

151

View full text Add to dashboard Cite

Abstract.A rapidly growing number of user and student modeling systems have employed numerical techniques for uncertainty management. The three major paradigms are those of Bayesian networks, the Dempster-Shafer theory of evidence, and fuzzy logic. In this overview, each of the first three main sections focuses on one of these paradigms. It first introduces the basic concepts by showing how they can be applied to a relatively simple user modeling problem. It then surveys systems that have applied techniques from the paradigm to user or student modeling, characterizing each system within a common framework. The final main section discusses several aspects of the usability of these techniques for user and student modeling, such as their knowledge engineering requirements, their need for computational resources, and the communicability of their results.

show abstract

“…We also used a dataset 2 that was previously used to evaluate abductive story understanding systems [24,6]. In this task, characters' higher-level plans must be inferred from their actions described in a narrative text.…”

Section: Story Understandingmentioning

confidence: 99%

Abductive Plan Recognition by Extending Bayesian Logic Programs

Raghavan

Mooney

2011

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Abstract. Plan recognition is the task of predicting an agent's top-level plans based on its observed actions. It is an abductive reasoning task that involves inferring cause from effect. Most existing approaches to plan recognition use either first-order logic or probabilistic graphical models. While the former cannot handle uncertainty, the latter cannot handle structured representations. In order to overcome these limitations, we develop an approach to plan recognition using Bayesian Logic Programs (BLPs), which combine first-order logic and Bayesian networks. Since BLPs employ logical deduction to construct the networks, they cannot be used effectively for plan recognition. Therefore, we extend BLPs to use logical abduction to construct Bayesian networks and call the resulting model Bayesian Abductive Logic Programs (BALPs). We learn the parameters in BALPs using the Expectation Maximization algorithm adapted for BLPs. Finally, we present an experimental evaluation of BALPs on three benchmark data sets and compare its performance with the state-of-the-art for plan recognition.

show abstract

A Bayesian model of plan recognition

Cited by 303 publications

References 3 publications

Recognizing Probabilistic Opponent Movement Models

Recognizing Probabilistic Opponent Movement Models

Numerical uncertainty management in user and student modeling: An overview of systems and issues

Abductive Plan Recognition by Extending Bayesian Logic Programs

Contact Info

Product

Resources

About