Improved Demonstration-Knowledge Utilization in Reinforcement Learning

Yanyu Liu, Yifeng Zeng, Biyang Ma, Yinghui Pan, Huifan Gao, Yuting Zhang

Research output: Contribution to journalArticlepeer-review


Reinforcement learning has made great success in recent years. Generally, the learning process requires a huge amount of interaction with the environment before an agent can achieve acceptable performance. This motivates many techniques, such as incorporating prior knowledge which is usually presented as experts’ demonstration, and using a probability distribution to represent state-and-action values, to accelerate the learning process. The methods perform well when the prior knowledge is genuinely correct and no much change occurs to the learning environment. However, the requirement is not perfectly realistic in many complex applications. The demonstration knowledge may not reflect the true environment and even be full of noise. In this paper, we introduce a dynamic distribution merging method to improve knowledge utilization in a general reinforcement learning algorithm, namely Q-learning. The new method adapts a normal distribution to represent state-action values and merges the prior and learned knowledge in a discriminative way. We theoretically analyze the new learning method and demonstrate its empirical performance over multiple problem domains.
Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalIEEE Transactions on Artificial Intelligence
Early online date3 Nov 2023
Publication statusE-pub ahead of print - 3 Nov 2023

Cite this