Fictional Co-Play for Human-Agent Collaboration
Evaluating state-of-the-art reinforcement learning technique for adaptability to human collaborators
N.A. Ordonez Cardenas (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Frans Oliehoek – Mentor (TU Delft - Interactive Intelligence)
R.T. Loftin – Graduation committee member (TU Delft - Interactive Intelligence)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
A longstanding problem in the area of reinforcement learning is human-agent col- laboration. As past research indicates that RL agents undergo a distributional shift when they start collaborating with human beings, the goal is to create agents that can adapt. We build upon research using the two-player Overcooked environment to repro- duce a simplified version of the Fictitious Co-Play algorithm in order to confirm past found improvements at a smaller scale of training and using Self-Play and Population- based trained algorithms as the baselines for comparison. We find that the agent on average slightly outperforms both baseline algorithms when evaluated using a human proxy. We also find high cross-seed variance in performance, indicating the potential for further hyperparameter tuning.