Approximate Bayesian inference in spatial environments
This addresses the problem of developing flexible, data-driven approaches for agents in spatial environments, though it is incremental as it builds on existing variational inference and neural network frameworks.
The paper tackled spatial decision-making tasks like localization and navigation by framing them as probabilistic inference under deep sequential generative models, achieving performance comparable to specialized state-of-the-art methods in two simulated environments.
Model-based approaches bear great promise for decision making of agents interacting with the physical world. In the context of spatial environments, different types of problems such as localisation, mapping, navigation or autonomous exploration are typically adressed with specialised methods, often relying on detailed knowledge of the system at hand. We express these tasks as probabilistic inference and planning under the umbrella of deep sequential generative models. Using the frameworks of variational inference and neural networks, our method inherits favourable properties such as flexibility, scalability and the ability to learn from data. The method performs comparably to specialised state-of-the-art methodology in two distinct simulated environments.