Keyphrases
- markov decision processes
- optimal policy
- state space
- transition matrices
- finite state
- reinforcement learning
- dynamic programming
- decentralized control
- infinite horizon
- finite horizon
- policy iteration
- control system
- model based reinforcement learning
- markov decision process
- planning under uncertainty
- state abstraction
- decision theoretic planning
- control problems
- partially observable
- reinforcement learning algorithms
- reachability analysis
- risk sensitive
- factored mdps
- average cost
- control policies
- action sets
- reward function
- average reward
- decision processes
- partially observable markov decision processes
- optimal control