Let's Do the Time Warp Again: Human Action Assistance for Reinforcement Learning Agents.
Carter B. BurnFrederick L. CrabbeRebecca HwaPublished in: ICAART (1) (2021)
Keyphrases
- human actions
- reinforcement learning agents
- action recognition
- dynamic environments
- spatio temporal
- reinforcement learning
- human motion
- space time
- human activities
- video sequences
- state abstraction
- action classification
- activity recognition
- visual features
- transfer learning
- view invariant
- motion recognition
- recognizing actions
- multi agent
- multi agent environments
- computer vision
- path finding
- state space
- multi agent systems
- learning algorithm
- machine learning