Learning from Observation Using Primitives
Learning without any prior knowledge in environments that contain large or continuous state spaces is a daunting task. For robots that operate in the real world, learning must occur in a reasonable amount of time. Providing a robot with domain knowledge and also with the ability to learn from watchi...
Main Author: | Bentivegna, Darrin Charles |
---|---|
Format: | Others |
Language: | en_US |
Published: |
Georgia Institute of Technology
2005
|
Subjects: | |
Online Access: | http://hdl.handle.net/1853/5100 |
Similar Items
-
New Approach in Human-AI Interaction by Reinforcement-Imitation Learning
by: Neda Navidi, et al.
Published: (2021-03-01) -
Deep Reinforcement Learning for Soft, Flexible Robots: Brief Review with Impending Challenges
by: Sarthak Bhagat, et al.
Published: (2019-01-01) -
Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy
by: Nicolas Duminy, et al.
Published: (2021-01-01) -
Hybrid Trajectory and Force Learning of Complex Assembly Tasks: A Combined Learning Framework
by: Yan Wang, et al.
Published: (2021-01-01) -
Episodic Self-Imitation Learning with Hindsight
by: Tianhong Dai, et al.
Published: (2020-10-01)