Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning.
Anusha NagabandiGregory KahnRonald S. FearingSergey LevinePublished in: CoRR (2017)
Keyphrases
- model free
- fine tuning
- reinforcement learning
- neural network
- reinforcement learning algorithms
- function approximation
- viable alternative
- temporal difference
- fine tune
- artificial neural networks
- state space
- policy iteration
- function approximators
- policy evaluation
- reinforcement learning methods
- dynamic model
- dynamical systems
- pattern recognition
- fine tuned
- optimal control
- average reward
- optimal policy
- multi agent
- rl algorithms
- genetic algorithm
- learning problems
- supervised learning
- learning algorithm
- machine learning