Learning by Observation of Agent Software Images

02/04/2014
by   Paulo Roberto Costa, et al.
0

Learning by observation can be of key importance whenever agents sharing similar features want to learn from each other. This paper presents an agent architecture that enables software agents to learn by direct observation of the actions executed by expert agents while they are performing a task. This is possible because the proposed architecture displays information that is essential for observation, making it possible for software agents to observe each other. The agent architecture supports a learning process that covers all aspects of learning by observation, such as discovering and observing experts, learning from the observed data, applying the acquired knowledge and evaluating the agents progress. The evaluation provides control over the decision to obtain new knowledge or apply the acquired knowledge to new problems. We combine two methods for learning from the observed information. The first one, the recall method, uses the sequence on which the actions were observed to solve new problems. The second one, the classification method, categorizes the information in the observed data and determines to which set of categories the new problems belong. Results show that agents are able to learn in conditions where common supervised learning algorithms fail, such as when agents do not know the results of their actions a priori or when not all the effects of the actions are visible. The results also show that our approach provides better results than other learning methods since it requires shorter learning periods.

READ FULL TEXT
research
05/04/2018

Behavioral Cloning from Observation

Humans often learn how to perform tasks via imitation: they observe othe...
research
06/12/2020

Learning to Communicate Using Counterfactual Reasoning

This paper introduces a new approach for multi-agent communication learn...
research
06/24/2022

Learning Rhetorical Structure Theory-based descriptions of observed behaviour

In a previous paper, we have proposed a set of concepts, axiom schemata ...
research
11/12/2015

Software Agents with Concerns of their Own

We claim that it is possible to have artificial software agents for whic...
research
03/22/2017

Independently Controllable Features

Finding features that disentangle the different causes of variation in r...
research
07/15/2019

On Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems

While many multiagent algorithms are designed for homogeneous systems (i...
research
10/05/2019

The Role of A-priori Information in Networks of Rational Agents

Until now, distributed algorithms for rational agents have assumed a-pri...

Please sign up or login with your details

Forgot password? Click here to reset