Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity
This is an incremental improvement for reinforcement learning practitioners seeking faster training convergence.
The paper tackles the problem of slow convergence in Q-learning by incorporating similarity between states and actions, resulting in significantly better performance compared to classic Q-learning as shown in numerical examples.
An improvement of Q-learning is proposed in this paper. It is different from classic Q-learning in that the similarity between different states and actions is considered in the proposed method. During the training, a new updating mechanism is used, in which the Q value of the similar state-action pairs are updated synchronously. The proposed method can be used in combination with both tabular Q-learning function and deep Q-learning. And the results of numerical examples illustrate that compared to the classic Q-learning, the proposed method has a significantly better performance.