Generalized Value Iteration Networks: Life Beyond Lattices

Understand

In this paper, we introduce a generalized value iteration network (GVIN), which is an end-to-end neural network planning module.

• GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs.
• We propose three novel differentiable kernels as graph convolution operators and show that the embedding based kernel achieves the best performance.
• We further propose episodic Q-learning, an improvement upon traditional n-step Q-learning that stabilizes training for networks that contain a planning module.