AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Generative Temporal Models with Spatial Memory for Partially Observed Environments

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

ICML 2018 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a low-dimensional state-space model for agent dynamics and a DND to store position–visual-feature pairsGTM-SM · CelebA image navigationlong-term prediction coherenceImproved
Use a rotation-aware state transition and periodic angle distances for memory retrievalGTM-SM · Labyrinth rotating agentprediction coherenceImproved
Model momentum, friction, and displacement saturation in the state transitionGTM-SM · Labyrinth walking agentstate prediction accuracyImproved
Add a regression loss using true displacements as targetsGTM-SM walking-agent model · Labyrinth walking agenttransition learningImproved
Use retrieved views in a Generative Query Network prior to combine views across projective transformationsGTM-SM · Labyrinth rotating agentprediction coherence for unseen viewpointsImproved
Test the single-room-trained model in larger multi-room environmentsGTM-SM walking-agent model · Labyrinth multi-room environmentsmemory of previously visited room texturesImproved
Generate corridors between rooms using a model trained only on single roomsGTM-SM walking-agent model · Labyrinth multi-room environmentscorridor renderingHurt
Generate complex objects with the VAE in the low-resolution Labyrinth imagesGTM-SM walking-agent model · Labyrinth walking agentobject renderingHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy