scholarly journals Learning in Bayesian Games with Binary Actions

2009 ◽  
Vol 9 (1) ◽  
Author(s):  
Alan Beggs
Keyword(s):  
Global Convergence ◽  
Learning Process ◽  
Adaptive Learning ◽  
Limit Point ◽  
Learning Rule ◽  
Potential Games ◽  
Unique Equilibrium ◽  
Supermodular Games ◽  
Bayesian Games ◽  
Convergence Results

This paper considers a simple adaptive learning rule in Bayesian games with binary actions where players employ threshold strategies. Global convergence results are given for supermodular games and potential games. If there is a unique equilibrium, players' strategies converge almost surely to it. Even if there is not, in potential games and in the two-player case in supermodular games, any limit point of the learning process must be an equilibrium. In particular, if equilibria are isolated, the learning process converges to one of them almost surely.

scholarly journals Strict lower subdifferentiability and applications

1999 ◽  
Vol 40 (3) ◽  
pp. 379-391 ◽  
Author(s):  
H. Xu ◽  
A. M. Rubinov ◽  
B. M. Glover
Keyword(s):  
Global Convergence ◽  
Optimality Conditions ◽  
Convex Subset ◽  
Sufficient Optimality Conditions ◽  
Descent Direction ◽  
Minimization Problems ◽  
Convergence Results ◽  
Lower Subdifferential ◽  
Necessary And Sufficient ◽  
Convex Subdifferential

AbstractWe investigate the strict lower subdifferentiability of a real-valued function on a closed convex subset of Rn. Relations between the strict lower subdifferential, lower subdifferential, and the usual convex subdifferential are established. Furthermore, we present necessary and sufficient optimality conditions for a class of quasiconvex minimization problems in terms of lower and strict lower subdifferentials. Finally, a descent direction method is proposed and global convergence results of the consequent algorithm are obtained.

Wind Shear Encountered Landing Control Based on CMACs

2013 ◽  
Vol 284-287 ◽  
pp. 2351-2355 ◽  
Author(s):  
Jih Gau Juang ◽  
Chung Ju Cheng ◽  
Teng Chieh Yang
Keyword(s):  
Intelligent Control ◽  
Adaptive Learning ◽  
Wind Shear ◽  
Learning Rule ◽  
Lyapunov Theory ◽  
Intelligent Control System ◽  
Automatic Landing ◽  
Control Scheme ◽  
Shear Condition ◽  
Landing Control

This paper presents an intelligent control scheme that uses different cerebellar model articulation controllers (CMACs) in aircraft automatic landing control. The proposed intelligent control system can act as an experienced pilot and guide the aircraft landed safely in wind shear condition. Lyapunov theory is applied to obtain adaptive learning rule and stability analysis is also provided. Furthermore, the proposed controllers are implemented in a DSP. The simulations by MatLab are demonstrated.

Learning in multi-team systems: a qualitative study of learning triggers, readiness to learn and learning processes

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Valerie I. Sessa ◽  
Jessica L. Francavilla ◽  
Manuel London ◽  
Marlee Wanamaker
Keyword(s):  
Case Studies ◽  
Learning Process ◽  
Adaptive Learning ◽  
Quantitative Research ◽  
Participant Observation ◽  
Learning Processes ◽  
Future Research ◽  
Content Type ◽  
First Case ◽  
Readiness To Learn

Purpose Multi-team systems (MTSs) are expected to respond effectively to complex challenges while remaining responsive and adaptable and preserving inter-team linking mechanisms. The leadership team of an MTS is expected to configure and reconfigure component teams to meet the unique needs of each situation and perform. How do they learn to do this? This paper, using a recent MTS learning theory as a basis, aims to begin to understand how MTSs learn and stimulate ideas for future research. Design/methodology/approach The authors use two case studies to address research questions. The first case was a snapshot in time, while the second case occurred over several months. Interviews, documents and participant observation were the data sources. Findings As suggested by theory, findings support the idea that learning triggers, the timing of the triggers and readiness to learn (RtL) affect the type of learning process that emerges. The cases showed examples of adaptive and generative team learning. Strong and clear triggers, occurring during performance episodes, led to adaptive learning. When RtL was high and triggers occurred during hiatus periods, the associated learning process was generative. Originality/value Using an available theoretical model and case studies, the research describes how MTS readiness to learn and triggers for learning affect MTS learning processes and how learning outcomes became codified in the knowledge base or structure of the MTS. This provides a framework for subsequent qualitative and quantitative research.

Ambiguity and context learning in signalling games

2020 ◽  
Author(s):  
Liping Tang
Keyword(s):  
Natural Language ◽  
Learning Process ◽  
Adaptive Learning ◽  
Structural Evolution ◽  
Sufficient Condition ◽  
Natural Languages ◽  
Context Learning ◽  
Ambiguous Words ◽  
Lattice Network ◽  
Signalling Games

Abstract Lexical ambiguity is present in many natural languages, but ambiguous words and phrases do not seem to be advantageous. Therefore, the presence of ambiguous words in natural language warrants explanation. We justify the existence of ambiguity from the perspective of context dependence. The main contribution of the paper is that we constructed a context learning process such that each interlocutor can infer their opponent’s private belief from the conversation. A sufficient condition for successful learning is provided. Furthermore, for cases in which learning fails, we investigate how the interlocutors choose among degrees of ambiguous expressions through an adaptive learning process. Lastly, we apply our model in the lattice network, demonstrating that structural evolution favours ambiguity as well.

Global convergence results for single parent evolution strategies

2016 ◽  
Vol 40 (17) ◽  
pp. 6192-6207
Author(s):  
Mohamed Jebalia ◽  
Anis Khlaifi ◽  
Fethi Bin Muhammad Belgacem
Keyword(s):  
Global Convergence ◽  
Single Parent ◽  
Evolution Strategies ◽  
Convergence Results
Sign in / Sign up

Export Citation Format

Share Document