Neural networks and differential dynamic programming for reinforcement learning problems.
Akihiko YamaguchiChristopher G. AtkesonPublished in: ICRA (2016)
Keyphrases
- reinforcement learning problems
- dynamic programming
- neural network
- markov decision problems
- function approximators
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- function approximation
- policy iteration
- linear programming
- fuzzy logic
- reinforcement learning methods
- optimal policy
- decision theoretic
- artificial neural networks
- partially observable
- transition probabilities
- model free
- learning algorithm
- action space
- radial basis function
- infinite horizon
- dynamical systems
- least squares
- genetic algorithm