A Deep Q-Learning Agent for the L-Game with Variable Batch Training
This is an incremental improvement for game AI, specifically in board games with sparse rewards.
The paper tackled training an agent for the L-Game using Deep Q-Learning with variable batch training to handle rare rewards and large action spaces, resulting in strong play without search methods or domain knowledge.
We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in order to mitigate the loss of the rare reward signal and significantly accelerate training. Despite the large action space due to the number of possible moves, the low-dimensional state space and the rarity of rewards, which only come at the end of a game, DQL is successful in training an agent capable of strong play without the use of any search methods or domain knowledge.