Improvements in Imitation Learning for Overcooked

Improvements in Imitation Learning for Overcooked

Niemantsverdriet, Duuk (TU Delft Electrical Engineering, Mathematics and Computer Science)

Loftin, R.T. (mentor)
Oliehoek, F.A. (mentor)
Hildebrandt, K.A. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2023-06-28

Arguably the main goal of artificial intelligence is to create agents that can collaborate with humans to achieve a shared goal. It has been shown that agents that assume their partner to be optimal can converge to protocols that humans do not understand. Taking human suboptimality into consideration is imperative to perform well in a coordination task. One way to achieve this is imitation learning, where you train an agent on recorded data from a human playing optimally. I created several agents using different implementations of behavioral cloning, by reducing the dataset to state-action pairs and training a neural network on this. To evaluate their performance, I used an environment that poses a coordination challenge based on the popular game Overcooked. Neither expanding nor reducing the feature space that the agents are trained on yielded any significant improvement in the performance of the agents. In fact, expanding the feature space to include some historical data made the agent less generalizable and especially failed to perform when paired with agents with unfamiliar strategies. These limitations were mostly posed by the available dataset, which was not big enough to support more features and of too low quality of gameplay to create agents that perform exceptionally well.

imitation learning
behavioral cloning
Overcooked AI
artificial intelligence
cooperative artificial intelligence

http://resolver.tudelft.nl/uuid:32294bd2-93a2-4456-8b34-9982c8406e0f

GitHub repository which contains all the code that I worked with: https://github.com/DuukPN/overcooked_ai

Student theses

bachelor thesis

© 2023 Duuk Niemantsverdriet