Hybrid Online and Offline Reinforcement Learning for Tibetan Jiu Chess

Abstract

In this study, hybrid state-action-reward-state-action (SARSAλ) and Q-learning algorithms are applied to different stages of an upper confidence bound applied to tree search for Tibetan Jiu chess. Q-learning is also used to update all the nodes on the search path when each game ends. A learning strategy that uses SARSAλ and Q-learning algorithms combining domain knowledge for a feedback function for layout and battle stages is proposed. An improved deep neural network based on ResNet18 is used for self-play training. Experimental results show that hybrid online and offline reinforcement learning with a deep neural network can improve the game program’s learning efficiency and understanding ability for Tibetan Jiu chess.

Model-free voltage control of active distribution system with PVs using surrogate model-based deep reinforcement learning

“…Since there is no interaction between the agent and physical model of ADN during training, this method can achieve physical model-free control. However, it requires a large amount of training data and distribution mismatch may degrade the performance of the algorithm even when sufficiently large and diverse data are given [33]. Ref.…”