Neuroevolution for deep reinforcement learning problems.
David HaPublished in: GECCO (Companion) (2018)
Keyphrases
- reinforcement learning problems
- function approximators
- reinforcement learning algorithms
- function approximation
- reinforcement learning
- neural network
- reinforcement learning methods
- temporal difference
- state space
- artificial neural networks
- markov decision problems
- learning tasks
- model free
- markov decision processes
- radial basis function
- real valued
- weight vector
- policy iteration
- search algorithm