Reducing hardware experiments for model learning and policy optimization.
Sehoon HaKatsu YamanePublished in: ICRA (2015)
Keyphrases
- prior knowledge
- learning process
- learning scheme
- supervised learning
- machine learning
- experimental data
- computational model
- learning algorithm
- real time
- optimization process
- learning tasks
- mathematical model
- optimization procedure
- learning models
- parameter estimation
- low cost
- probabilistic model
- cost function
- reinforcement learning
- decision trees