Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning.
Anusha NagabandiGregory KahnRonald S. FearingSergey LevinePublished in: ICRA (2018)
Keyphrases
- model free
- fine tuning
- reinforcement learning
- neural network
- reinforcement learning algorithms
- function approximation
- temporal difference
- fine tune
- viable alternative
- fine tuned
- policy iteration
- state space
- rl algorithms
- dynamic model
- function approximators
- policy evaluation
- machine learning
- dynamical systems
- radial basis function
- artificial neural networks
- pattern recognition
- genetic algorithm
- impedance control
- markov decision processes
- temporal difference learning
- image classification