Continuous Deep Q-Learning with Model-based Acceleration.
Shixiang GuTimothy P. LillicrapIlya SutskeverSergey LevinePublished in: ICML (2016)
Keyphrases
- model free
- reinforcement learning
- state space
- cooperative
- function approximation
- learning algorithm
- continuous state spaces
- multi agent
- reinforcement learning algorithms
- stochastic approximation
- neural network
- multi agent reinforcement learning
- search space
- knowledge base
- dynamic environments
- optimal policy
- data mining
- learning rate
- real time