Keyphrases
- guided exploration
- model based reinforcement learning
- markov decision processes
- optimal policy
- exploratory learning
- markov decision problems
- multilayer perceptron
- neural network
- policy iteration
- reinforcement learning
- infinite horizon
- markov decision process
- reward function
- average cost
- finite state
- decision processes
- linear programming
- state space
- partially observable
- machine learning
- action space
- dynamic programming
- active learning