Keyphrases
- markov decision processes
- computational cost
- data structure
- state space
- learning algorithm
- significant improvement
- reinforcement learning
- theoretical analysis
- optimal policy
- orders of magnitude
- neural network
- computational complexity
- dynamic programming
- policy iteration
- machine learning algorithms
- factored mdps
- partially observable markov decision processes
- infinite horizon
- computationally efficient
- worst case
- decision trees