Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning.
Jaskirat SinghLiang ZhengPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- three dimensional
- multi agent
- multiple images
- dynamic environments
- scene understanding
- d scene
- estimation algorithm
- dynamic scenes
- function approximation
- outdoor scenes
- high dimensional
- learning algorithm
- image regions
- uncalibrated cameras
- scene classification
- visual attention
- single image
- state space
- image sequences
- computer vision