Keyphrases
- optimal policy
- markov decision process
- markov decision processes
- reward function
- markov decision problems
- state space
- reinforcement learning
- decision problems
- policy search
- control policies
- finite state
- bayesian reinforcement learning
- dynamic programming
- policy iteration
- infinite horizon
- discounted reward
- total reward
- small sized
- sufficient conditions
- average reward
- initial state
- average cost
- linear program
- finite horizon
- utility function
- heuristic search
- stationary policies
- management policies
- learning algorithm
- partially observable markov decision processes
- long run