Learning Tree Structured Potential Games
نویسندگان
چکیده
Many real phenomena, including behaviors, involve strategic interactions that can be learned from data. We focus on learning tree structured potential games where equilibria are represented by local maxima of an underlying potential function. We cast the learning problem within a max margin setting and show that the problem is NP-hard even when the strategic interactions form a tree. We develop a variant of dual decomposition to estimate the underlying game and demonstrate with synthetic and real decision/voting data that the game theoretic perspective (carving out local maxima) enables meaningful recovery.
منابع مشابه
Challenging Games or Digital Textbooks? Content analysis of message structure and learning principles in serious games
Previous studies on game-based learning have proposed many factors that make video games good learning tools. This study uses content analysis to assess whether these theories are applied to the designs of web-based games for learning. The samples for this study are 90 pro-environmental video games randomly sample from the internet. Results from this study showed that despite the assumptions th...
متن کاملTree-connected peer group situations and peer group games
A class of cooperative games is introduced which arises from situations in which a set of agents is hierarchically structured and where potential individual economic abilities interfere with the behavioristic rules induced by the organization structure. These games form a cone generated by a specific class of unanimity games, namely those based on coalitions called peer groups. Different econom...
متن کاملRelationship between Designing Computer-based Educational Games, and Learning Motivation among Elementary Students
Background: Motivation is an important factor in learning. Educational games increase the learning motivation and understanding of students by creating a sense of joy, satisfaction and involvement. However, it is necessary to incorporate learning elements into the games, differently. In this study, the researcher tried to provide a model for designing educational games and determining its relat...
متن کاملLearning from Queries and Examples with Tree-structured Bias
Incorporating declarative bias or prior knowledge into learning is an active research topic in machine learning. Tree-structured bias speciies the prior knowledge as a tree of \relevance" relationships between attributes. This paper presents a learning algorithm that implements tree-structured bias, i.e., learns any target function probably approximately correctly from random examples and membe...
متن کاملTreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need to be learned from data, the deficiencies of learned models have limited their...
متن کامل