Simulating the Evolution of Homeless Populations in Canada Using Modified Deep Q-Learning (MDQL) and Modified Neural Fitted Q-Iteration (MNFQ) Algorithms.
Andrew FisherVijay MagoEric LatimerPublished in: IEEE Access (2020)
Keyphrases
- learning algorithm
- fitted q iteration
- reinforcement learning
- row column
- cooperative
- united states
- significant improvement
- computational cost
- neural network
- optimization problems
- convergence rate
- orders of magnitude
- machine learning algorithms
- evolutionary algorithm
- computational efficiency
- data structure
- learning rate
- stochastic approximation
- multi agent reinforcement learning
- case study
- machine learning