Enhancing the episodic natural actor-critic algorithm by a regularisation term to stabilize learning of control structures

Abstract

Incomplete or imprecise models of control systems make it difficult to find an appropriate structure and parameter set for a corresponding control policy. These problems are addressed by reinforcement learning algorithms like policy gradient methods. We describe how to stabilise the policy gradient descent by introducing a regularisation term to enhance the episodic natural actor-critic approach. This allows a more policy independent usage.