Belief Revision for Inductive Game Theory
نویسندگان
چکیده
Inductive game theory captures how a player inductively derives his/her personal views from experiences. The player may have multiple views, some of which differ from the objective situation, but may revise them with further experiences. This paper gives a logical formulation of this revision process by focusing on the role of player’s beliefs. For this objective, we take the AGM approach of belief revision. The idea behind our logic is that the player’s belief state is represented by a belief set of propositional formulas, thereby describing a revision process for the belief states by using a revision operation in AGM theory. In this setting, the player’s personal views are described as models for the current belief set. We also present an application of our framework to a class of inductive games, called festival games.
منابع مشابه
“Survey” of Formal Epistemology: Some Propaganda, and an Example
What is “Formal Epistemology”? Not sure, really. I first heard the term from Sahotra Sarkar in 2003 . It seems that it is quite a broad field, which includes: Ampliative inference (including inductive logic); Game theory and decision theory; Formal learning theory; Formal theories of coherence: Foundations of probability and statistics; Formal approaches to paradoxes of belief and/or act...
متن کاملIterated belief revision, reliability, and inductive amnesia
Belief revision theory concerns methods for reformulating an agent’s epistemic state when the agent’s beliefs are refuted by new information. The usual guiding principle in the design of such methods is to preserve as much of the agent’s epistemic state as possible when the state is revised. Learning theoretic research focuses, instead, on a learning method’s reliability or ability to converge ...
متن کاملKnowledge acquisition from complex domains by combining inductive learning and theory revision
In the process of knowledge acquisition, inductive learning and theory revision play important roles. Inductive learning is used to acquire new knowledge (theories) from training examples; and theory revision improves an initial theory with training examples. A theory preference criterion is critical in the processes of inductive learning and theory revision. A new system called knowar is devel...
متن کاملPseudo Extension and Belief Revision in Default Reasoning
This paper is concerned with the extension and the belief revision in Reiter's default reasoning. First we introduce a new notion of pseudo exten sion which is successively constructed from a given default theory. We show that the set of pseudo extensions contains the set of extensions, so that we can get some reasonable candidates of extension in a constructive way. This should be a first step...
متن کاملA Three{tiered Conndence Model for Revising Logical Theories
The task of theory revision in Inductive Logic Programming is to correct the current theory when contradictions with new examples arise. Conndence models are used to assess and compare the diierent alternatives of revising a theory in order to choose the best revision. In this paper, we propose an augmentation of the two{tiered conndence model of MOBAL/KRT that allows to combine diierent heuris...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011