Causal Reinforcement Learning in Robotics Applications

Our goal is to create an environment for the robots to participate in a cooperative situation and collaborate with other robots and human on cooperating task. Games like Hanabi and Block Stacking problems are good examples of goal-oriented and cooperation focused problem-solving tasks that will lead us to implement an algorithm that can be applied on intelligent systems.
In this project our aim is to create a real environment using our tools and equipment at Queen’s University Lab to cooperate with the robot arm (Sawyer) and reach the task goals. Considering the fact that human and robot interaction creates an uncertain environment we are looking to solve the issue by developing the algorithms with human causal learning abilities.

Faculty Supervisor:

Sidney Givigi

Student:

Partner:

Institut Supérieur de l'Aéronautique et de l'Espace

Discipline:

Computer science

Sector:

Education

University:

Queen's University

Program: