Generalized Value Iteration Networks: Life Beyond Lattices
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. Lastly, we evaluate GVIN on planning problems in 2D mazes, irregular graphs, and real-world street networks, showing that GVIN generalizes well for both arbitrary graphs and unseen graphs of larger scale and outperforms a naive generalization of VIN (discretizing a spatial graph into a 2D image).
Code (1)
Tasks
Q-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Disorder in cellular packing can alter proliferation dynamics to regulate growth
Controlling growth via cell division is crucial in the development of higher organisms, and yet the mechanisms through which this is achieved, e.g., in epithelial tissue, is not yet fully understood. We show that by coup…
Algebraic Models for Qualified Aggregation in General Rough Sets, and Reasoning Bias Discovery
In the context of general rough sets, the act of combining two things to form another is not straightforward. The situation is similar for other theories that concern uncertainty and vagueness. Such acts can be endowed w…
Modeling premiums of non-life insurance companies in India
We undertake an empirical analysis for the premium data of non-life insurance companies operating in India, in the paradigm of fitting the data for the parametric distribution of Lognormal and the extreme value based dis…
Generalized Second Order Value Iteration in Markov Decision Processes
Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied …
Reinforcement LearningSparse Generalized Eigenvalue Problem via Smooth Optimization
In this paper, we consider an $\ell_{0}$-norm penalized formulation of the generalized eigenvalue problem (GEP), aimed at extracting the leading sparse generalized eigenvector of a matrix pair. The formulation involves m…