Learning Summarised Messaging Through Mediated Differentiable Inter-Agent Learning

2020 ◽  
pp. 546-557
Author(s):  
Sharan Gopal ◽  
Rishabh Mathur ◽  
Shaunak Deshwal ◽  
Anil Singh Parihar
Keyword(s):  
Agent Learning

scholarly journals Of pride and prejudice: agent learning under sticky and persistent stereotype

2021 ◽  
Vol 16 (2) ◽  
pp. 381-410
Author(s):  
Georg D. Blind ◽  
Stefania Lottanti von Mandach
Keyword(s):  
Maximum Likelihood ◽  
Private Equity ◽  
Optimum Level ◽  
Pride And Prejudice ◽  
Anglo Saxon ◽  
Agent Learning ◽  
Economic Interaction ◽  
Level Of Effort ◽  
Group Agents ◽  
A Share

AbstractStereotypes matter for economic interaction if counterparty utility is informed by factors other than price. Stereotyped agents may engage in efforts to counter stereotype by adapting to in-group standards. We present a model informing the optimal extent of these efforts depending on an agent’s (a) share of total transactions between out- and in-group agents; and (b) share of repeated transaction pairings with in-group counterparties. Low values of (a) suppress the effect of adaptation efforts on the stereotype itself (persistence). In turn, low values of (b) mean that out-group agents cannot dissociate from stereotype (stickiness). Significantly, the model implies that the optimum level of effort may require adaptation beyond in-group standards, and that such over-adaptation attains maximum likelihood in cases where stereotype is sticky and persistent at the same time. We test our model with data on private equity buyout investments conducted in Japan between 1998 and 2015 by domestic Japanese and Anglo-Saxon funds. We document that the latter not only adapt, but eventually over-adapt. In addition, we show that their efforts are effective in reducing a premium initially asked by domestic counterparties.

scholarly journals User-Centric Radio Access Technology Selection: A Survey of Game Theory Models and Multi-Agent Learning Algorithms

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Giuseppe Caso ◽  
Ozgu Alay ◽  
Guido Carlo Ferrante ◽  
Luca De Nardis ◽  
Maria-Gabriella Di Benedetto ◽  
...  
Keyword(s):  
Game Theory ◽  
Learning Algorithms ◽  
Technology Selection ◽  
Access Technology ◽  
Radio Access Technology ◽  
Radio Access ◽  
Agent Learning ◽  
Multi Agent ◽  
User Centric ◽  
Radio Access Technology Selection

Hierarchical Reinforcement Learning

2021 ◽  
Vol 54 (5) ◽  
pp. 1-35
Author(s):  
Shubham Pateria ◽  
Budhitama Subagdja ◽  
Ah-hwee Tan ◽  
Chai Quek
Keyword(s):  
Reinforcement Learning ◽  
Future Research ◽  
Comprehensive Overview ◽  
Open Problems ◽  
Practical Applications ◽  
Hierarchical Reinforcement Learning ◽  
The Past ◽  
Agent Learning ◽  
Multi Agent ◽  
Supplementary Material

Hierarchical Reinforcement Learning (HRL) enables autonomous decomposition of challenging long-horizon decision-making tasks into simpler subtasks. During the past years, the landscape of HRL research has grown profoundly, resulting in copious approaches. A comprehensive overview of this vast landscape is necessary to study HRL in an organized manner. We provide a survey of the diverse HRL approaches concerning the challenges of learning hierarchical policies, subtask discovery, transfer learning, and multi-agent learning using HRL. The survey is presented according to a novel taxonomy of the approaches. Based on the survey, a set of important open problems is proposed to motivate the future research in HRL. Furthermore, we outline a few suitable task domains for evaluating the HRL approaches and a few interesting examples of the practical applications of HRL in the Supplementary Material.

scholarly journals A Proposed Model for Detecting Learning Styles Based on Agent Learning

2016 ◽  
Vol 11 (10) ◽  
pp. 65 ◽  
Author(s):  
M S Hasibuan ◽  
L E Nugroho ◽  
P I Santosa ◽  
S S Kusumawardani
Keyword(s):  
Learning Styles ◽  
Learning Style ◽  
Evaluation Model ◽  
Learning System ◽  
Learning Activities ◽  
Instructional Materials ◽  
Data Driven ◽  
Automatic Learning ◽  
Proposed Model ◽  
Agent Learning

A learning style is an issue related to learners. In one way or the other, learning style could assist learners in their learning activities if students ignore their learning styles, it may influence their effort in understanding teaching materials. To overcome these problems, a model for reliable automatic learning style detection is needed. Currently, there are two approaches in detecting learning styles: data driven and literature based. Learners, especially those with changing learning styles, have difficulties in adopting these two approach since they are not adaptive, dynamic and responsive (ADR). To solve the above problems, a model using agent learning approach is proposes. Agent learning involves performing activities in four phases, i.e. initialization, learning, matching and, recommendations to decide the learning styles the students use. The proposed system will provide instructional materials that match the learning style that has been detected. The automatics detection process is performed by combining the data-driven and literature-based approaches. We propose an evaluation model agent learning system to ensure the model is working properly.

scholarly journals Comparison of the efficiency of two algorithms which solve the shortest path problem with an emotional agent

2006 ◽  
Vol 16 (2) ◽  
pp. 211-226 ◽  
Author(s):  
Silvana Petruseva
Keyword(s):  
Shortest Path ◽  
Polynomial Algorithm ◽  
Optimal Solution ◽  
Agent Architecture ◽  
Multiplicative Constant ◽  
Goal State ◽  
The Neural Network ◽  
Starting State ◽  
Agent Learning ◽  
One Step

This paper discusses the comparison of the efficiency of two algorithms, by estimation of their complexity. For solving the problem, the Neural Network Crossbar Adaptive Array (NN-CAA) is used as the agent architecture, implementing a model of an emotion. The problem discussed is how to find the shortest path in an environment with n states. The domains concerned are environments with n states, one of which is the starting state, one is the goal state, and some states are undesirable and they should be avoided. It is obtained that finding one path (one solution) is efficient, i.e. in polynomial time by both algorithms. One of the algorithms is faster than the other only in the multiplicative constant, and it shows a step forward toward the optimality of the learning process. However, finding the optimal solution (the shortest path) by both algorithms is in exponential time which is asserted by two theorems. It might be concluded that the concept of subgoal is one step forward toward the optimality of the process of the agent learning. Yet, it should be explored further on, in order to obtain an efficient, polynomial algorithm.

Sign in / Sign up

Export Citation Format

Share Document