Continuous Deep Q-Learning with Model-based Acceleration.
Shixiang GuTimothy P. LillicrapIlya SutskeverSergey LevinePublished in: CoRR (2016)
Keyphrases
- model free
- reinforcement learning
- cooperative
- continuous state spaces
- multi agent
- state space
- function approximation
- data driven
- learning algorithm
- optimal policy
- multi agent systems
- case study
- reinforcement learning algorithms
- fully unsupervised
- search space
- neural network
- optimal control
- learning rate
- discrete space