Mastering the Card Game of Jaipur Through Zero-Knowledge Self-Play Reinforcement Learning and Action Masks.

Cristina Cutajar Josef Bajada

Published in: AI*IA (2023)

Keyphrases

card game
reinforcement learning
imperfect information
knowledge acquisition
perfect information
knowledge base
domain knowledge
state space
domain experts
computer programs
dynamic programming
upper bound
optimal policy
human experts
learning process
expert systems
lower bound
card games