Robust Markov Decision Processes using Sigma Point sampling.
Luca F. BertuccelliJonathan P. HowPublished in: ACC (2008)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- risk sensitive
- transition matrices
- decision theoretic planning
- average reward
- policy iteration
- planning under uncertainty
- reinforcement learning algorithms
- finite horizon
- action space
- decision processes
- state abstraction
- model based reinforcement learning
- average cost
- partially observable
- state and action spaces
- reachability analysis
- sample size
- factored mdps
- action sets
- semi markov decision processes
- machine learning