Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning
Confirmation: I accept the constraint that If the paper will be accepted at least one of the authors will attend the workshop and present the work
Keywords: reinforcement learning, interpretability, generalizability, memory, closed drafting
Abstract: Closed drafting or "pick and pass" is a popular game mechanic where each round players select a card or other playable element from their hand and pass the rest to the next player. In this paper, we establish first-principle methods for studying the interpretability, generalizability, and memory of Deep Q-Network (DQN) models playing closed drafting games. In particular, we use a popular family of closed drafting games called "Sushi Go Party", in which we achieve state-of-the-art performance. We fit decision rules to interpret the decision-making strategy of trained DRL agents by comparing them to the ranking preferences of different types of human players. As Sushi Go Party can be expressed as a set of closely-related games based on the set of cards in play, we quantify the generalizability of DRL models trained on various sets of cards, establishing a method to benchmark agent performance as a function of environment unfamiliarity. Using the explicitly calculable memory of other player's hands in closed drafting games, we create measures of the ability of DRL models to learn memory.
Supplementary file: https://anonymous.4open.science/r/xai-7031/XAI4DRL_Supp_ClosedDrafting.zip
Submission Type: Short Paper
Submission Number: 1
Loading