Robust adaptive Markov Decision Processes in multi-vehicle applications.
Luca F. BertuccelliBrett BethkeJonathan P. HowPublished in: ACC (2009)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- policy iteration
- transition matrices
- planning under uncertainty
- reinforcement learning algorithms
- reachability analysis
- decision theoretic planning
- finite horizon
- partially observable
- decision processes
- infinite horizon
- risk sensitive
- average cost
- action space
- average reward
- model based reinforcement learning
- factored mdps
- search algorithm
- markov decision process
- reward function
- state and action spaces
- total reward
- dynamical systems
- machine learning