Please use this identifier to cite or link to this item:
Title: Q-learning in collaborative multiagent systems
Author: González Trastoy, Alfred
Director: López Sánchez, Maite
Keywords: Aprenentatge automàtic
Intel·ligència artificial
Treballs de fi de grau
Aprenentatge per reforç (Intel·ligència artificial)
Processos de Markov
Machine learning
Artificial intelligence
Computer software
Bachelor's thesis
Reinforcement learning
Markov processes
Issue Date: Feb-2018
Abstract: Q-learning is one of the most widely used reinforcement learning techniques. It is very effective for learning an optimal policy in any finite Markov decision process (MDP). Collaborative multiagent systems, though, are a challenge for self-interested agent implementation, as higher utility can be achieved via collaboration. To evaluate the Q-learning efficiency in collaborative multiagent systems, we will use a simplified version of the Malmo Collaborative AI Challenge (MCAC). It was designed by Microsoft and consists of a game where 2 players can collaborate to catch the pig (high reward) or leave the game (low reward). Each action costs 1, so knowing when to leave and when to chase the pig is key for achieving high scores. Two main problems are faced in the challenge: uncertainty of the other agent behaviour and a limited learning time. We propose solutions to both problems using a simplified MCAC environment, a stateaction abstraction and an agent type modelling. We have implemented an agent that is able to identify the other player behaviour (whether it is collaborating or not) and can learn an optimal policy against each type of player. Results show that Q-learning is an efficient and effective technique to solve collaborative multiagent systems.
Note: Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2018, Director: Maite López Sánchez
Appears in Collections:Programari - Treballs de l'alumnat
Treballs Finals de Grau (TFG) - Enginyeria Informàtica

Files in This Item:
File Description SizeFormat 
codi_font.zipCodi font656.72 kBzipView/Open
memoria.pdfMemòria1.33 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons