Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Student works
  4. Multi-agent Reinforcement Learning for Assembly of a Spanning Structure
 
master thesis

Multi-agent Reinforcement Learning for Assembly of a Spanning Structure

Vallat, Gabriel  
January 20, 2023

In this master thesis, multi-agent reinforcement learning is used to teach robots to build a self-supporting structure connecting two points. To accomplish this task, a physics simulator is first designed using linear programming. Then, the task of building a self-supporting structure is modeled as a Markov game, where the robot arms correspond to the agents of the game. This formalism is then used to design learning agents and train them using deep reinforcement learning. Two different types of deep neural network models, based on image analysis and graph theory, respectively, are used to develop their policy. The agents are then trained either centrally or distributively to compare their learning processes and weaknesses. In a final experiment, the efficiency of the learning algorithm Soft Actor-Critic, is compared to Advantage Actor-Critic, highlighting the effectiveness of using Shannon entropy to search through the policy space. Finally, the training procedure allows agents to successfully build a structure that spans ten times the width of the building blocks without the need to use any binding between them or a removable scaffold during assembly.

  • Files
  • Details
  • Metrics
Type
master thesis
Author(s)
Vallat, Gabriel  
Advisors
Kamgarpour, Maryam  
•
Parascho, Stefana  
Date Issued

2023-01-20

Total of pages

55

Subjects

Multi-agent Reinforcement learning

•

Soft Actor-Critic

•

Graph Neural Networks

EPFL units
SYCAMORE  
CRCL  
Available on Infoscience
December 21, 2023
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/202738
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés