genetic programming – Pedro Sequeira

Socio-Emotional IMRL

Socio-Emotional Reward Design for Intrinsically-Motivated Reinforcement Learning Agents – C# code

Source repository: https://github.com/pedrodbs/SocioEmotionalIMRL

This repository contains the code used to produce the results in my PhD thesis. The code implements the intrinsically-motivated reinforcement learning (IRML) framework, an extension to RL where an agent is rewarded for behaviors other than those strictly related to the task being accomplished, e.g., by exploring or playing with elements of its environment.

Genetica.NET

A genetic programming library written in C#

Source repository: https://github.com/pedrodbs/Genetica

Genetica is a .NET open-source genetic programming (GP) library written entirely in C#. Currently, Genetica.NET supports the evolution of programs representing mathematical expressions in a syntactic tree form. Mathematical programs combine primitives taken from a set of terminals, representing input scalar values, and several mathematical functions.

Automated Cognitive Behavior Analysis

Understanding and predicting human behavior has always been a fundamental research question in AI. This project proposes a methodology to address that problem termed automated cognitive behavior analysis (ACBA). The methodology allows uncovering the underlying behavior structures — the mental plans guiding and shaping people’s actions carried out in the world — given observed behavior performed in the context of complex tasks. It involves the use of genetic programming (GP) to iteratively generate programs capable of explaining the behavior exhibited by an individual in a given task. It also includes a set of tools to help analyze and interpret the invariant cognitive structures responsible for different observed behaviors.

Intrinsically-Motivated Reinforcement Learning

My Ph.D thesis focused in developing flexible and robust mechanisms for autonomous agents by using the computational framework of reinforcement learning (RL). Within the field of machine learning, RL is the discipline concerned with providing mechanisms that allow an agent to accomplish a task through trial-and-error interactions with a dynamic and sometimes uncertain and unreliable environment. Furthermore, agents usually suffer from perceptual, motor and adaptive limitations, i.e., they often do not have access to “all” the information required to make the best decisions and normally do not know the environment’s dynamics or the exact consequences of their actions. As a consequence, standard RL techniques present several design challenges, especially when dealing with complex problems often involving a great amount of fine-tuning and user expert knowledge.

Learning and Emotions

A great portion of my Ph.D thesis was dedicated to incorporating ideas from the emotional processing mechanisms in humans and other animals into the framework of intrinsically-motivated reinforcement learning (IMRL). Emotions are one of the most basic behavioral phenomena observed in nature, yet they have often been considered as detrimental to rational and sound decision-making. However, as research in psychology, biology, neuroscience and other areas has shown, emotions are a beneficial adaptive mechanism for problem solving, enhancing perception, memory, attention and other cognitive skills.