Exploring multi-view perspectives on deep reinforcement learning agents for embodied object navigation in virtual home environments.
Xiaotian LiuVictoria ArmstrongSara NabilChristian MuisePublished in: CASCON (2021)
Keyphrases
- multi view
- d objects
- home environments
- reinforcement learning agents
- single view
- visual hull
- multiple views
- dynamic scenes
- three dimensional
- depth map
- pose estimation
- range data
- view synthesis
- viewpoint
- reinforcement learning
- multi view learning
- augmented reality
- semi supervised
- object tracking
- virtual reality
- intelligent agents
- virtual environment
- daily activities
- object recognition
- shape from silhouettes
- range images
- dynamic environments
- dynamic programming
- service robots
- home environment
- moving objects
- multi agent