Strategy Selection in Complex Game Environments Based on Transfer Reinforcement Learning

摘要

Boosting the learning process in the new task by making use of previously obtained knowledge has been a challenging task in many fields of industrial engineering and scientific. In this paper, we propose a transfer reinforcement learning model with knowledge Inheritance and decision-making Assistance (trIA). In the stage of knowledge inheritance, trIA adopts a model that employs a simultaneous multi-task and multi-instance learning strategy to compress acquired experts knowledge from distinct task into a global multi-task agent. In the stage of decision-making assistance, trIA adopts a dual-column progressive neural network framework to fully utilize the previous knowledge in the global multi-task agent and the acquired knowledge in the new task. The experimental results on the Atari domain demonstrate that the proposed knowledge inheritance model can performed at nearly the same level as the experts on the distinct source task environments. The results also demonstrate that the decision-making assistance model can transfer knowledge from the source tasks to the target tasks effectively. Moreover, the comparative results with the state-ofthe-art algorithms validate the effectiveness of the proposed trIA for strategy selection in complex game environments.