Generative Temporal Models with Spatial Memory for Partially Observed Environments

By Marco Fraccaro, Danilo Jimenez Rezende, Yori Zwols, Alexander Pritzel, S. M. Ali Eslami, Fabio Viola. 2018

29 citations recorded by the source corpus.

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic environments, due to the difficulty of training such models in larger, potentially partially-observed and 3D environments. In this work we introduce a novel action-conditioned generative model of such challenging environments. The model features a non-parametric spatial memory system in which we store learned, disentangled representations of the environment. Low-dimensional spatial updates are computed using a state-space model that makes use of knowledge on the prior dynamics of the moving agent, and high-dimensional visual observations are modelled with a Variational Auto-Encoder. The result is a scalable architecture capable of performing coherent predictions over hundreds of time steps across a range of partially observed 2D and 3D environments.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Shaping Belief States with Generative Environment Models for RL (2019, background): “A fundamental problem in building useful environment models, which we want to address in this work, is long-term consistency [11, 12].”
On the link between conscious function and general intelligence in humans and machines (2022, background): “This can be achieved through either increasing the training data, or incorporating relevant inductive biases: for instance, using geometry for localization within 3D Euclidean domains (Rosenbaum et al., 2018; Fraccaro et al., 2018).”
Graph Element Networks: adaptive, structured computation and memory (2019, methodology): “Notably, Fraccaro et al. (2018) used differentiable neural dictionaries (DNDs) (Pritzel et al., 2017) to solve a problem similar to our scene representation exper-iment in section 4.3.”