Using reinforcement learning to adapt an imitation task.
Florent GuenterAude BillardPublished in: IROS (2007)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- reinforcement learning algorithms
- learning algorithm
- markov decision processes
- imitation learning
- machine learning
- supervised learning
- direct policy search
- optimal policy
- multi agent
- least squares
- dynamic programming
- learning classifier systems
- temporal difference
- objective function
- learning agent
- control policy
- learning agents
- reinforcement learning methods
- data mining
- real time