Deep Q-learning: a robust control approach

Abstract

In this paper, we place deep Q-learning into a control-oriented perspective and study its learning dynamics with well-established techniques from robust control. We formulate an uncertain linear time-invariant model by means of the neural tangent kernel to describe learning. We show the instability of learning and analyze the agent's behavior in frequency-domain. Then, we ensure convergence via robust controllers acting as dynamical rewards in the loss function. We synthesize three controllers: state-feedback gain scheduling H2, dynamic Hinf, and constant gain Hinf controllers. Setting up the learning agent with a control-oriented tuning methodology is more transparent and has well-established literature compared to the heuristics in reinforcement learning. In addition, our approach does not use a target network and randomized replay memory. The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer). Numerical simulations in different OpenAI Gym environments suggest that the Hinf controlled learning performs slightly better than Double deep Q-learning.

References in corpus (7)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Explainable Machine Learning for Scientific Insights and Discoveries
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning
• Deep Reinforcement Learning and the Deadly Triad
• Observe and Look Further: Achieving Consistent Performance on Atari
• Towards Characterizing Divergence in Deep Q-Learning