Accelerating Reinforcement Learning through Implicit Imitation.
Bob PriceCraig BoutilierPublished in: J. Artif. Intell. Res. (2003)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- temporal difference
- model free
- optimal control
- optimal policy
- multi agent
- machine learning
- imitation learning
- markov decision processes
- dynamic programming
- learning process
- action selection
- reinforcement learning algorithms
- control problems
- direct policy search
- supervised learning
- domain knowledge
- artificial neural networks
- case study
- function approximators
- temporal difference learning
- data sets
- robotic control