Keyphrases
- markov decision processes
- sample complexity
- theoretical analysis
- learning problems
- upper bound
- lower bound
- special case
- reinforcement learning
- supervised learning
- optimal policy
- learning algorithm
- finite state
- policy iteration
- generalization error
- dynamic programming
- state space
- average reward
- active learning
- training examples
- infinite horizon
- sample size
- finite horizon
- markov decision process
- planning under uncertainty
- action space
- risk sensitive
- average cost
- partially observable
- transition matrices
- learning tasks
- partially observable markov decision processes
- factored mdps