アクセスログ分析における接頭部分列からのプラン認識

Plan recognition is a key component of player modeling. Player plan recognition focuses on modeling how and when players select goals and formulate action sequences to achieve their goals during gameplay. By occasionally asking players to describe their plans, it is possible to devise robust plan recognition models that jointly reason about player goals and action sequences in coordination with player input. In this work, we present a player plan recognition framework that leverages data from player interactions with a planning support tool embedded in an educational game for middle school science education, CRYSTAL ISLAND. Players are prompted to use the planning tool to describe their goals and planned actions in CRYSTAL ISLAND. We use this data to devise data-driven player plan recognition models using multi-label multi-task learning. Specifically, we compare single-task and multi-task learning approaches for both goal prediction and action sequence prediction. Results indicate that multi-task learning yields significant benefits for action sequence prediction. Additionally, we find that incorporating automated detectors of plan completion in plan recognition models improves predictive performance in both tasks.

Plan recognition aims to discover target plans (i.e., sequences of actions) behind observed actions, with history plan libraries or domain models in hand. Previous approaches either discover plans by maximally matching observed actions to plan libraries, assuming target plans are from plan libraries, or infer plans by executing domain models to best explain the observed actions, assuming complete domain models are available. In real world applications, however, target plans are often not from plan libraries and complete domain models are often not available, since building complete sets of plans and complete domain models are often difficult or expensive. In this paper we view plan libraries as corpora and learn vector representations of actions using the corpora; we then discover target plans based on the vector representations. Our approach is capable of discovering underlying plans that are not from plan libraries, without requiring domain models provided. We empirically demonstrate the effectiveness of our approach by comparing its performance to traditional plan recognition approaches in three planning domains.

Plan recognition is a process of the observers inferring agents’ goal and planning by observing the agents’ behavior sequences. It is applied to image processing, network security and military domain. But the most prior work about plan recognition could not deal with fragmentary and small quantity of event information effectively and accurately. In this paper, we put forward an event-driven plan recognition method based on intuitionistic fuzzy theory. The algorithm based on recognizing the fuzzy event sequences is presented to forecast the future action about object. First, by analyzing the process and feature of plan recognition, we bring the master plan into sub-tasks which are a sequence of events, and then we create an algorithm about predicting the goal of the plan by recognizing the series of events. At the same time, thinking about the uncertainty of event, intuitionistic fuzzy theory is put into this model to eliminate the ambiguity of data. Finally, an experiment in military domain is testified for our approach.

We study an incremental process of learning where a set of generic basic actions are used to learn higher-level task-dependent action sequences. A task-dependent action sequence is learned by associating the goal given by a human demonstrator with the task-independent, general-purpose actions in the action repertoire. This process of contextualization is done using probabilistic parsing. We propose stochastic context-free grammars as the representational framework due to its robustness to noise, structural flexibility, and easiness on defining task-independent actions. We demonstrate our implementation on a real-world scenario using a humanoid robot and report implementation issues we had.

The output of a GMTI tracker (such as the VS-IMM) over an extended period of time can be viewed as generating a string sequence (namely the mode sequence) that defines the trajectory. In previous work, it was demonstrated with real data that the target trajectory could be (probabilistically) parsed in real-time, assuming any string sequence output from the tracker could arise only from a stochastic context-free grammar (SCFG). In this paper, an GMTI data processing chain, with a view towards the application to syntactic parsing, is presented. An emphasis is placed on the Bayesian formualtions, which provides a unified description of the processing algorithms.

The hypnogram is a schematic representation of sleep dynamics as a sequence of stages along the night. The authors have shown, in previous work, the adequacy of syntactic modeling in automatic sleep analysis. According to this approach, the hypnogram is viewed as expression of a language whose temporal organization is described by stochastic context-free grammars. Here, the authors propose a hybrid model combining syntactic and semantic information, where stage duration is taken into account in terms of attributed grammars. This model enables hypnogram simulation, by means of language generation, and provides improvement in classification accuracy. The method is applied in automatic hypnogram analysis of a control group and a population of dysthymic patients.

Plan recognition is the process of inferring other agents' plans and goals based on their observable actions. Essentially all previous work in plan recognition has focused on the recognition process itself, with no regard to the use of the information in the recognizing agent. As a result, low-likelihood recognition hypotheses that may imply significant meaning to the observer, are ignored in existing work. In this paper, we present novel efficient algorithms that allows the observer to incorporate her own biases and preferences---in the form of a utility function---into the plan recognition process. This allows choosing recognition hypotheses based on their expected utility to the observer. We call this Utility-based Plan Recognition (UPR). We briefly discuss a hybrid symbolic decision-theoretic plan recognizer, and demonstrate the efficacy of this approach in an example.

Plan recognition is a focus of Artificial Intelligence. In this paper, combined with a flexible planning approach, a flexible plan recognition method which is based on the flexible planning is given, and the construction process of flexible planning is supplied. Based on these, we design the method of flexible goal graph extending, give the main theoretical analysis of the goal graph, and greatly reduce the flexibility of the size of the goal graph by using the pruning method. At the same time, it limits the scope that the agent can do in planning. The algorithm can get the most reasonable plan that the observed agent may adopt in a lot of planning space.

This paper bases on the formal theoretical research of this plan recognition model, it preliminary studied the plan recognition technology; it is based on the functional characteristics from intelligent plan recognition theory, which one of the most important hotspots in the research field of artificial intelligence.It can analyze the presumable multi-target states that will be achieved by attacker and it can effectively identify the final target state attacker may achieve.Therefore, it can realize the response process to the invasive action of the attacker.

Offensive or antagonistic language targeted at individuals and social groups based on their personal characteristics (also known as cyber hate speech or cyberhate) has been frequently posted and widely circulated via the World Wide Web. This can be considered as a key risk factor for individual and societal tension surrounding regional instability. Automated Web-based cyberhate detection is important for observing and understanding community and regional societal tension—especially in online social networks where posts can be rapidly and widely viewed and disseminated. While previous work has involved using lexicons, bags-of-words, or probabilistic language parsing approaches, they often suffer from a similar issue, which is that cyberhate can be subtle and indirect—thus, depending on the occurrence of individual words or phrases, can lead to a significant number of false negatives, providing inaccurate representation of the trends in cyberhate. This problem motivated us to challenge thinking around the representation of subtle language use, such as references to perceived threats from “the other” including immigration or job prosperity in a hateful context. We propose a novel “othering” feature set that utilizes language use around the concept of “othering” and intergroup threat theory to identify these subtleties, and we implement a wide range of classification methods using embedding learning to compute semantic distances between parts of speech considered to be part of an “othering” narrative. To validate our approach, we conducted two sets of experiments. The first involved comparing the results of our novel method with state-of-the-art baseline models from the literature. Our approach outperformed all existing methods. The second tested the best performing models from the first phase on unseen datasets for different types of cyberhate, namely religion, disability, race, and sexual orientation. The results showed F-measure scores for classifying hateful instances obtained through applying our model of 0.81, 0.71, 0.89, and 0.72, respectively, demonstrating the ability of the “othering” narrative to be an important part of model generalization.

Previous empirical work on animal social learning has found that many species lack the ability to learn entire action sequences solely through reliance on social information. Conversely, acquiring action sequences through asocial learning can be difficult due to the large number of potential sequences arising from even a small number of base actions. In spite of this, several studies report that some primates use action sequences in the wild. We investigate how social information can be integrated with asocial learning to facilitate the learning of action sequences. We formalize this problem by examining how learners using temporal difference learning, a widely applicable model of reinforcement learning, can combine social cues with their own experiences to acquire action sequences. The learning problem is modeled as a Markov decision process. The learning of nettle processing by mountain gorillas serves as a focal example. Through simulations, we find that the social facilitation of component actions can combine with individual learning to facilitate the acquisition of action sequences. Our analysis illustrates that how even simple forms of social learning, combined with asocial learning, generate substantially faster learning of action sequences compared to asocial processes alone, and that the benefits of social information increase with the length of the action sequence and the number of base actions.

Kinematic boundary cues modulate 12-month-old infants’ segmentation of action sequences: An ERP study

Toddlers’ action prediction: Statistical learning of continuous action sequences

In this paper, we study the problem of procedure planning in instructional videos. Here, an agent must produce a plausible sequence of actions that can transform the environment from a given start to a desired goal state. When learning procedure planning from instructional videos, most recent work leverages intermediate visual observations as supervision, which requires expensive annotation efforts to localize precisely all the instructional steps in training videos. In contrast, we remove the need for expensive temporal video annotations and propose a weakly supervised approach by learning from natural language instructions. Our model is based on a transformer equipped with a memory module, which maps the start and goal observations to a sequence of plausible actions. Furthermore, we augment our model with a probabilistic generative module to capture the uncertainty inherent to procedure planning, an aspect largely overlooked by previous work. We evaluate our model on three datasets and show our weakly-supervised approach outperforms previous fully supervised state-of-the-art models on multiple metrics.

Natural language interfaces for robot control aspire to find the best sequence of actions that reflect the behavior intended by the instruction. This is difficult because of the diversity of language, variety of environments, and heterogeneity of tasks. Previous work has demonstrated that probabilistic graphical models constructed from the parse structure of natural language can be used to identify motions that most closely resemble verb phrases. Such approaches however quickly succumb to computational bottlenecks imposed by construction and search the space of possible actions. Planning constraints, which define goal regions and separate the admissible and inadmissible states in an environment model, provide an interesting alternative to represent the meaning of verb phrases. In this paper we present a new model called the Distributed Correspondence Graph (DCG) to infer the most likely set of planning constraints from natural language instructions. A trajectory planner then uses these planning constraints to find a sequence of actions that resemble the instruction. Separating the problem of identifying the action encoded by the language into individual steps of planning constraint inference and motion planning enables us to avoid computational costs associated with generation and evaluation of many trajectories. We present experimental results from comparative experiments that demonstrate improvements in efficiency in natural language understanding without loss of accuracy.