Neuroevolution for deep reinforcement learning problems.
David HaPublished in: GECCO (Companion) (2019)
Keyphrases
- reinforcement learning problems
- function approximators
- reinforcement learning algorithms
- function approximation
- reinforcement learning
- reinforcement learning methods
- state space
- temporal difference
- model free
- markov decision problems
- markov decision processes
- learning tasks
- policy iteration
- neural network
- action space
- artificial neural networks
- learning algorithm
- dynamic environments
- linear programming
- mobile robot
- decision making
- machine learning