A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning.
Abdalkarim MohtasibGerhard NeumannHeriberto CuayáhuitlPublished in: TAROS (2021)
Keyphrases
- reinforcement learning
- empirical studies
- learning algorithm
- active learning
- mobile robot
- simulated robot
- undergraduate students
- visual learning
- autonomous robots
- learning process
- computer assisted instruction
- robot control
- skill learning
- optimal policy
- action selection
- elementary school
- vision system
- autonomous learning
- credit assignment