A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning.
Abdalkarim MohtasibGerhard NeumannHeriberto CuayáhuitlPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- empirical studies
- learning process
- goal directed
- elementary school
- learning algorithm
- mobile robot
- visual learning
- learning tasks
- dictionary learning
- undergraduate students
- action selection
- human teacher
- learning systems
- mobile learning
- vision system
- long run
- robot navigation
- high school students
- skill learning