Results 11 - 20
of
22
Are you thinking what I’m thinking? An Evaluation of a Simplified Theory of Mind
"... Abstract. We examine the effectiveness of an agent’s approximate theory of mind when interacting with human players in a wartime negotiation game. We first measure how accurately the agent’s theory of mind captured the players ’ actual behavior. We observe significant overlap between the players ’ b ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. We examine the effectiveness of an agent’s approximate theory of mind when interacting with human players in a wartime negotiation game. We first measure how accurately the agent’s theory of mind captured the players ’ actual behavior. We observe significant overlap between the players ’ behavior and the agents ’ idealized expectations, but we also observe significant deviations. Forming an incorrect expectation about a person is not inherently damaging, so we then analyzed how different deviations affected the game outcomes. We observe that many classes of inaccuracy in the agent’s theory of mind did not hurt the agent’s performance and, in fact, some of them played to the agent’s benefit. The results suggest potential advantages to giving an agent a computational model of theory of mind that is overly simplified, especially as a first step when investigating a domain with as much uncertainty as wartime negotiation.
Approximating Behavioral Equivalence of Models Using Top-K Policy Paths
"... Decision making and game play in multiagent settings must often contend with behavioral models of other agents in order to predict their actions. One approach that reduces the complexity of the unconstrained model space is to group models that tend to be behaviorally equivalent. In this paper, we se ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Decision making and game play in multiagent settings must often contend with behavioral models of other agents in order to predict their actions. One approach that reduces the complexity of the unconstrained model space is to group models that tend to be behaviorally equivalent. In this paper, we seek to further compress the model space by introducing an approximate measure of behavioral equivalence and using it to group models. Categories and Subject Descriptors I.2.11 [Distributed Artificial Intelligence]: Multiagent systems
Decision Making in omplex Multiagent Contexts: A Tale of Two Frameworks
- AI MAGAZINE
, 2012
"... ..."
Speeding Up Solutions of Interactive Dynamic Influence Diagrams Using Action Equivalence ∗
"... Interactive dynamic influence diagrams (I-DIDs) are graphical models for sequential decision making in partially observable settings shared by other agents. Algorithms for solving I-DIDs face the challenge of an exponentially growing space of candidate models ascribed to other agents, over time. Pre ..."
Abstract
- Add to MetaCart
Interactive dynamic influence diagrams (I-DIDs) are graphical models for sequential decision making in partially observable settings shared by other agents. Algorithms for solving I-DIDs face the challenge of an exponentially growing space of candidate models ascribed to other agents, over time. Previous approach for exactly solving I-DIDs groups together models having similar solutions into behaviorally equivalent classes and updates these classes. We present a new method that, in addition to aggregating behaviorally equivalent models, further groups models that prescribe identical actions at a single time step. We show how to update these augmented classes and prove that our method is exact for some cases. The new approach enables us to bound the aggregated model space by the cardinality of other agents ’ actions. We evaluate its performance and provide empirical results in support. 1
Decentralized Partially-Observable Markov Decision Processes
"... outcome: window: [0,8] D Q Pr ..."
(Show Context)
Emotional Attachments for Story Construction in Virtual Game Worlds Sentiments of the Mind Module
"... In the virtual game world prototype World of Minds that uses the Mind Module, a semi-autonomous agent architecture, the notion of sentiments, or emotional attachments between objects, is what constitutes the deep structure in the game world. In this paper a play test is presented where sentiments ar ..."
Abstract
- Add to MetaCart
(Show Context)
In the virtual game world prototype World of Minds that uses the Mind Module, a semi-autonomous agent architecture, the notion of sentiments, or emotional attachments between objects, is what constitutes the deep structure in the game world. In this paper a play test is presented where sentiments are instantiated in three different ways; randomly, by choice of the player and through interaction. The test indicates that the sentiments that are instantiated through interaction between entities in the world are those that create meaning for they players of a quality that would be useful for the co-creation of narrative potential in virtual game worlds.
Iterative Online Planning in Multiagent Settings with Limited Model Spaces and PAC Guarantees
"... Methods for planning in multiagent settings often model other agents ’ possible behaviors. However, the space of these models – whether these are policy trees, finite-state controllers or inten-tional models – is very large and thus arbitrarily bounded. This may exclude the true model or the optimal ..."
Abstract
- Add to MetaCart
(Show Context)
Methods for planning in multiagent settings often model other agents ’ possible behaviors. However, the space of these models – whether these are policy trees, finite-state controllers or inten-tional models – is very large and thus arbitrarily bounded. This may exclude the true model or the optimal model. In this paper, we present a novel iterative algorithm for online planning that consid-ers a limited model space, updates it dynamically using data from interactions, and provides a provable and probabilistic bound on the approximation error. We ground this approach in the context of graphical models for planning in partially observable multiagent settings – interactive dynamic influence diagrams. We empirically demonstrate that the limited model space facilitates fast solutions and that the true model often enters the limited model space.
