The Experts below are selected from a list of 513 Experts worldwide ranked by ideXlab platform
James C Lester - One of the best experts on this subject based on the ideXlab platform.
-
Intelligent Narrative Technologies - Improving Goal Recognition in Interactive Narratives with Models of Narrative Discovery Events
2020Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Computational models of Goal Recognition hold considerable promise for enhancing the capabilities of drama managers and director agents for interactive narratives. The problem of Goal Recognition, and its more general form plan Recognition, has been the subject of extensive investigation in the AI community. However, there have been relatively few empirical investigations of Goal Recognition models in the intelligent narrative technologies community to date, and little is known about how computational models of interactive narrative can inform Goal Recognition. In this paper, we investigate a novel Goal Recognition model based on Markov Logic Networks (MLNs) that leverages narrative discovery events to enrich its representation of narrative state. An empirical evaluation shows that the enriched model outperforms a prior state-of-the-art MLN model in terms of accuracy, convergence rate, and the point of convergence.
-
Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks
Plan Activity and Intent Recognition, 2020Co-Authors: Eun Y Ha, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:In digital games Goal Recognition centers on identifying the concrete objectives that a player is attempting identifying the concrete objectives that a player is attempting to achieve given a domain model and a sequence of actions in a virtual environment. Goal-Recognition models in open-ended digital games introduce opportunities for adapting gameplay events based on the choices of individual players, as well as interpreting player behaviors during post hoc data mining analyses. However, Goal Recognition in open-ended games poses significant computational challenges, including inherent uncertainty, exploratory actions, and ill-defined Goals. This chapter reports on an investigation of Markov logic networks (MLNs) for recognizing player Goals in open-ended digital game environments with exploratory actions. The Goal-Recognition model was trained on a corpus collected from player interactions with an open-ended game-based learning environment known as C rystal I sland . We present experimental results, in which the Goal-Recognition model was compared to n -gram models. The findings suggest the proposed Goal-Recognition model yields significant accuracy gains beyond the n -gram models for predicting player Goals in an open-ended digital game.
-
a generalized multidimensional evaluation framework for player Goal Recognition
Artificial Intelligence and Interactive Digital Entertainment Conference, 2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
AIIDE - A Generalized Multidimensional Evaluation Framework for Player Goal Recognition
2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
player Goal Recognition in open world digital games with long short term memory networks
International Joint Conference on Artificial Intelligence, 2016Co-Authors: Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Recent years have seen a growing interest in player modeling for digital games. Goal Recognition, which aims to accurately recognize players' Goals from observations of low-level player actions, is a key problem in player modeling. However, player Goal Recognition poses significant challenges because of the inherent complexity and uncertainty pervading gameplay. In this paper, we formulate player Goal Recognition as a sequence labeling task and introduce a Goal Recognition framework based on long short-term memory (LSTM) networks. Results show that LSTM-based Goal Recognition is significantly more accurate than previous state-of-the-art methods, including n-gram encoded feedforward neural networks pre-trained with stacked denoising autoencoders, as well as Markov logic network-based models. Because of increased Goal Recognition accuracy and the elimination of labor-intensive feature engineering, LSTM-based Goal Recognition provides an effective solution to a central problem in player modeling for open-world digital games.
Bradford W Mott - One of the best experts on this subject based on the ideXlab platform.
-
Intelligent Narrative Technologies - Improving Goal Recognition in Interactive Narratives with Models of Narrative Discovery Events
2020Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Computational models of Goal Recognition hold considerable promise for enhancing the capabilities of drama managers and director agents for interactive narratives. The problem of Goal Recognition, and its more general form plan Recognition, has been the subject of extensive investigation in the AI community. However, there have been relatively few empirical investigations of Goal Recognition models in the intelligent narrative technologies community to date, and little is known about how computational models of interactive narrative can inform Goal Recognition. In this paper, we investigate a novel Goal Recognition model based on Markov Logic Networks (MLNs) that leverages narrative discovery events to enrich its representation of narrative state. An empirical evaluation shows that the enriched model outperforms a prior state-of-the-art MLN model in terms of accuracy, convergence rate, and the point of convergence.
-
Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks
Plan Activity and Intent Recognition, 2020Co-Authors: Eun Y Ha, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:In digital games Goal Recognition centers on identifying the concrete objectives that a player is attempting identifying the concrete objectives that a player is attempting to achieve given a domain model and a sequence of actions in a virtual environment. Goal-Recognition models in open-ended digital games introduce opportunities for adapting gameplay events based on the choices of individual players, as well as interpreting player behaviors during post hoc data mining analyses. However, Goal Recognition in open-ended games poses significant computational challenges, including inherent uncertainty, exploratory actions, and ill-defined Goals. This chapter reports on an investigation of Markov logic networks (MLNs) for recognizing player Goals in open-ended digital game environments with exploratory actions. The Goal-Recognition model was trained on a corpus collected from player interactions with an open-ended game-based learning environment known as C rystal I sland . We present experimental results, in which the Goal-Recognition model was compared to n -gram models. The findings suggest the proposed Goal-Recognition model yields significant accuracy gains beyond the n -gram models for predicting player Goals in an open-ended digital game.
-
a generalized multidimensional evaluation framework for player Goal Recognition
Artificial Intelligence and Interactive Digital Entertainment Conference, 2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
AIIDE - A Generalized Multidimensional Evaluation Framework for Player Goal Recognition
2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
player Goal Recognition in open world digital games with long short term memory networks
International Joint Conference on Artificial Intelligence, 2016Co-Authors: Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Recent years have seen a growing interest in player modeling for digital games. Goal Recognition, which aims to accurately recognize players' Goals from observations of low-level player actions, is a key problem in player modeling. However, player Goal Recognition poses significant challenges because of the inherent complexity and uncertainty pervading gameplay. In this paper, we formulate player Goal Recognition as a sequence labeling task and introduce a Goal Recognition framework based on long short-term memory (LSTM) networks. Results show that LSTM-based Goal Recognition is significantly more accurate than previous state-of-the-art methods, including n-gram encoded feedforward neural networks pre-trained with stacked denoising autoencoders, as well as Markov logic network-based models. Because of increased Goal Recognition accuracy and the elimination of labor-intensive feature engineering, LSTM-based Goal Recognition provides an effective solution to a central problem in player modeling for open-world digital games.
William Yeoh - One of the best experts on this subject based on the ideXlab platform.
-
game theoretic Goal Recognition models with applications to security domains
Decision and Game Theory for Security, 2017Co-Authors: Hau Chan, Albert Xin Jiang, William YeohAbstract:Motivated by the Goal Recognition (GR) and Goal Recognition design (GRD) problems in the artificial intelligence (AI) planning domain, we introduce and study two natural variants of the GR and GRD problems with strategic agents, respectively. More specifically, we consider game-theoretic (GT) scenarios where a malicious adversary aims to damage some target in an (physical or virtual) environment monitored by a defender. The adversary must take a sequence of actions in order to attack the intended target. In the GTGR and GTGRD settings, the defender attempts to identify the adversary’s intended target while observing the adversary’s available actions so that he/she can strengthens the target’s defense against the attack. In addition, in the GTGRD setting, the defender can alter the environment (e.g., adding roadblocks) in order to better distinguish the Goal/target of the adversary.
-
GameSec - Game-Theoretic Goal Recognition Models with Applications to Security Domains
Lecture Notes in Computer Science, 2017Co-Authors: Hau Chan, Albert Xin Jiang, William YeohAbstract:Motivated by the Goal Recognition (GR) and Goal Recognition design (GRD) problems in the artificial intelligence (AI) planning domain, we introduce and study two natural variants of the GR and GRD problems with strategic agents, respectively. More specifically, we consider game-theoretic (GT) scenarios where a malicious adversary aims to damage some target in an (physical or virtual) environment monitored by a defender. The adversary must take a sequence of actions in order to attack the intended target. In the GTGR and GTGRD settings, the defender attempts to identify the adversary’s intended target while observing the adversary’s available actions so that he/she can strengthens the target’s defense against the attack. In addition, in the GTGRD setting, the defender can alter the environment (e.g., adding roadblocks) in order to better distinguish the Goal/target of the adversary.
-
IJCAI - New Metrics and Algorithms for Stochastic Goal Recognition Design Problems
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. The Stochastic GRD (S-GRD) model is an important extension that introduced stochasticity to the outcome of agent actions. Unfortunately, the worst-case distinctiveness (wcd) metric proposed for S-GRDs has a formal definition that is inconsistent with its intuitive definition, which is the maximal number of actions an agent can take, in the expectation, before its Goal is revealed. In this paper, we make the following contributions: (1) We propose a new wcd metric, called all-Goals wcd (wcdag), that remedies this inconsistency; (2) We introduce a new metric, called expected-case distinctiveness (ecd), that weighs the possible Goals based on their importance; (3) We provide theoretical results comparing these different metrics as well as the complexity of computing them optimally; and (4) We describe new efficient algorithms to compute the wcdag and ecd values.
-
Goal Recognition design with stochastic agent action outcomes
International Joint Conference on Artificial Intelligence, 2016Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that the agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. Thus far, existing work assumes that the outcomes of the actions of the agents are deterministic, which might be unrealistic in real-world problems. For example, wheel slippage in robots cause the outcomes of their movements to be stochastic. In this paper, we generalize the GRD problem to Stochastic GRD (S-GRD) problems, which handle stochastic action outcomes. We also generalize the worst-case distinctiveness (wcd) measure, which measures the goodness of a solution, to take stochasticity into account. Finally, we introduce Markov decision process (MDP) based algorithms to compute the wcd and minimize it by making up to k actions infeasible.
-
IJCAI - Goal Recognition design with stochastic agent action outcomes
2016Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that the agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. Thus far, existing work assumes that the outcomes of the actions of the agents are deterministic, which might be unrealistic in real-world problems. For example, wheel slippage in robots cause the outcomes of their movements to be stochastic. In this paper, we generalize the GRD problem to Stochastic GRD (S-GRD) problems, which handle stochastic action outcomes. We also generalize the worst-case distinctiveness (wcd) measure, which measures the goodness of a solution, to take stochasticity into account. Finally, we introduce Markov decision process (MDP) based algorithms to compute the wcd and minimize it by making up to k actions infeasible.
Christabel Wayllace - One of the best experts on this subject based on the ideXlab platform.
-
stochastic Goal Recognition design
National Conference on Artificial Intelligence, 2019Co-Authors: Christabel WayllaceAbstract:Given an environment and a set of allowed modifications, the task of Goal Recognition design (GRD) is to select a valid set of modifications that minimizes the maximal number of steps an agent can take before its Goal is revealed to an observer. This document presents an extension of GRD to the stochastic domain: the Stochastic Goal Recognition Design (S-GRD). The GRD framework aims to consider: (1) Stochastic agent action outcomes; (2) Partial observability of agent states and actions; and (3) Suboptimal agents. In this abstract we present the progress made towards the final objective as well as a timeline of projected conclusion.
-
AAAI - Stochastic Goal Recognition Design
Proceedings of the AAAI Conference on Artificial Intelligence, 2019Co-Authors: Christabel WayllaceAbstract:Given an environment and a set of allowed modifications, the task of Goal Recognition design (GRD) is to select a valid set of modifications that minimizes the maximal number of steps an agent can take before its Goal is revealed to an observer. This document presents an extension of GRD to the stochastic domain: the Stochastic Goal Recognition Design (S-GRD). The GRD framework aims to consider: (1) Stochastic agent action outcomes; (2) Partial observability of agent states and actions; and (3) Suboptimal agents. In this abstract we present the progress made towards the final objective as well as a timeline of projected conclusion.
-
IJCAI - New Metrics and Algorithms for Stochastic Goal Recognition Design Problems
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. The Stochastic GRD (S-GRD) model is an important extension that introduced stochasticity to the outcome of agent actions. Unfortunately, the worst-case distinctiveness (wcd) metric proposed for S-GRDs has a formal definition that is inconsistent with its intuitive definition, which is the maximal number of actions an agent can take, in the expectation, before its Goal is revealed. In this paper, we make the following contributions: (1) We propose a new wcd metric, called all-Goals wcd (wcdag), that remedies this inconsistency; (2) We introduce a new metric, called expected-case distinctiveness (ecd), that weighs the possible Goals based on their importance; (3) We provide theoretical results comparing these different metrics as well as the complexity of computing them optimally; and (4) We describe new efficient algorithms to compute the wcdag and ecd values.
-
Goal Recognition design with stochastic agent action outcomes
International Joint Conference on Artificial Intelligence, 2016Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that the agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. Thus far, existing work assumes that the outcomes of the actions of the agents are deterministic, which might be unrealistic in real-world problems. For example, wheel slippage in robots cause the outcomes of their movements to be stochastic. In this paper, we generalize the GRD problem to Stochastic GRD (S-GRD) problems, which handle stochastic action outcomes. We also generalize the worst-case distinctiveness (wcd) measure, which measures the goodness of a solution, to take stochasticity into account. Finally, we introduce Markov decision process (MDP) based algorithms to compute the wcd and minimize it by making up to k actions infeasible.
-
IJCAI - Goal Recognition design with stochastic agent action outcomes
2016Co-Authors: Christabel Wayllace, William YeohAbstract:Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that the agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their Goals as early as possible. Thus far, existing work assumes that the outcomes of the actions of the agents are deterministic, which might be unrealistic in real-world problems. For example, wheel slippage in robots cause the outcomes of their movements to be stochastic. In this paper, we generalize the GRD problem to Stochastic GRD (S-GRD) problems, which handle stochastic action outcomes. We also generalize the worst-case distinctiveness (wcd) measure, which measures the goodness of a solution, to take stochasticity into account. Finally, we introduce Markov decision process (MDP) based algorithms to compute the wcd and minimize it by making up to k actions infeasible.
Jonathan P Rowe - One of the best experts on this subject based on the ideXlab platform.
-
Intelligent Narrative Technologies - Improving Goal Recognition in Interactive Narratives with Models of Narrative Discovery Events
2020Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Computational models of Goal Recognition hold considerable promise for enhancing the capabilities of drama managers and director agents for interactive narratives. The problem of Goal Recognition, and its more general form plan Recognition, has been the subject of extensive investigation in the AI community. However, there have been relatively few empirical investigations of Goal Recognition models in the intelligent narrative technologies community to date, and little is known about how computational models of interactive narrative can inform Goal Recognition. In this paper, we investigate a novel Goal Recognition model based on Markov Logic Networks (MLNs) that leverages narrative discovery events to enrich its representation of narrative state. An empirical evaluation shows that the enriched model outperforms a prior state-of-the-art MLN model in terms of accuracy, convergence rate, and the point of convergence.
-
Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks
Plan Activity and Intent Recognition, 2020Co-Authors: Eun Y Ha, Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:In digital games Goal Recognition centers on identifying the concrete objectives that a player is attempting identifying the concrete objectives that a player is attempting to achieve given a domain model and a sequence of actions in a virtual environment. Goal-Recognition models in open-ended digital games introduce opportunities for adapting gameplay events based on the choices of individual players, as well as interpreting player behaviors during post hoc data mining analyses. However, Goal Recognition in open-ended games poses significant computational challenges, including inherent uncertainty, exploratory actions, and ill-defined Goals. This chapter reports on an investigation of Markov logic networks (MLNs) for recognizing player Goals in open-ended digital game environments with exploratory actions. The Goal-Recognition model was trained on a corpus collected from player interactions with an open-ended game-based learning environment known as C rystal I sland . We present experimental results, in which the Goal-Recognition model was compared to n -gram models. The findings suggest the proposed Goal-Recognition model yields significant accuracy gains beyond the n -gram models for predicting player Goals in an open-ended digital game.
-
a generalized multidimensional evaluation framework for player Goal Recognition
Artificial Intelligence and Interactive Digital Entertainment Conference, 2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
AIIDE - A Generalized Multidimensional Evaluation Framework for Player Goal Recognition
2016Co-Authors: Alok Baikadi, Bradford W Mott, Jonathan P Rowe, Eun Young Ha, James C LesterAbstract:Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is Goal Recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player Goal Recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based Goal Recognition models. In this paper, we introduce GoalIE, a multidimensional framework for evaluating player Goal Recognition models. The framework integrates multiple metrics for player Goal Recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GoalIE framework with the evaluation of several player Goal Recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based Goal recognizers on two different educational games. The results suggest that GoalIE effectively captures Goal Recognition behaviors that are key to next-generation player modeling.
-
player Goal Recognition in open world digital games with long short term memory networks
International Joint Conference on Artificial Intelligence, 2016Co-Authors: Bradford W Mott, Jonathan P Rowe, James C LesterAbstract:Recent years have seen a growing interest in player modeling for digital games. Goal Recognition, which aims to accurately recognize players' Goals from observations of low-level player actions, is a key problem in player modeling. However, player Goal Recognition poses significant challenges because of the inherent complexity and uncertainty pervading gameplay. In this paper, we formulate player Goal Recognition as a sequence labeling task and introduce a Goal Recognition framework based on long short-term memory (LSTM) networks. Results show that LSTM-based Goal Recognition is significantly more accurate than previous state-of-the-art methods, including n-gram encoded feedforward neural networks pre-trained with stacked denoising autoencoders, as well as Markov logic network-based models. Because of increased Goal Recognition accuracy and the elimination of labor-intensive feature engineering, LSTM-based Goal Recognition provides an effective solution to a central problem in player modeling for open-world digital games.
