Natural Language Processing and Reinforcement Learning to Generate Morally

Natural Language Processing and Reinforcement Learning to Generate Morally: What is the optimal weight w to win the games while playing morally?

Boudier, Kenzo (TU Delft Electrical Engineering, Mathematics and Computer Science)

Liscio, E. (mentor)
Mambelli, D. (mentor)
Murukannaiah, P.K. (mentor)
Yang, J. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2023-07-03

In our everyday life, people interact more and more with agents. However these agents often lack a moral sense and prioritize the accomplishment of the given task. In consequence, agents may unknowingly act immorally. Little research or progress has been done to endow agents with human morality and an internal sense of right and wrong. As of today, agents have a primitive representation of morality often represented as 1 value. In contrast, humans have multiple reasons to judge an action as moral. In hope of creating agents that are imbued with a more complex and human moral, we build upon the Jiminy Cricket environment. This preexisting environment has multiple games with diverse scenarios and the objective is to do the most moral action to maximize the reward

NLP
MFT
RL

http://resolver.tudelft.nl/uuid:9b72f10d-577e-4433-8b10-15cf964112d5

Student theses

bachelor thesis

© 2023 Kenzo Boudier