Batch reinforcement learning for optimizing longitudinal driving assistance strategies.
Olivier PietquinFabio TangoRaghav ArasPublished in: CIVTS (2011)
Keyphrases
- control system
- reinforcement learning
- control strategies
- batch mode
- function approximation
- multi agent reinforcement learning
- learning agents
- search strategies
- neural network
- active learning
- exploration strategy
- batch size
- learning agent
- reinforcement learning algorithms
- optimal strategy
- optimal control
- markov decision processes
- optimal policy
- state space
- knowledge base
- learning algorithm
- machine learning