Accession Number:

ADA621833

Title:

Learning in the Presence of Unawareness

Descriptive Note:

Final rept. 1 Jul 2009-30 Jun 2013

Corporate Author:

CORNELL UNIV ITHACA NY

Personal Author(s):

• Halpern, Joseph

Report Date:

2015-01-27

Pagination or Media Count:

9.0

Abstract:

The standard assumption in game theory and decision theory is that the gamedecision problem is, in a sense, completely understood. For example, decision problems are typically described in terms of states and outcomes, where acts are taken to be functions from states to outcomes. It is typically assumed that a decision maker DM knows the state space, the outcome space, and the set of feasible acts. But this is far from clear in practice. In a complex decision problem, agents may be unaware of many relevant features, and thus unaware of possible states, outcomes, and feasible acts.

Descriptors:

• *DECISION THEORY
• *LEARNING MACHINES
• *UNCERTAINTY
• BEHAVIOR
• COMPUTER LOGIC
• GAME THEORY
• KNOWLEDGE MANAGEMENT
• MULTIAGENT SYSTEMS
• REASONING
• SEMANTICS
• SITUATIONAL AWARENESS
• STATISTICAL ANALYSIS
• WEIGHTING FUNCTIONS

Subject Categories:

• Operations Research
• Human Factors Engineering and Man Machine Systems

Distribution Statement:

APPROVED FOR PUBLIC RELEASE