Dueling Network Architectures for Deep Reinforcement Learning.
Ziyu WangTom SchaulMatteo HesselHado van HasseltMarc LanctotNando de FreitasPublished in: ICML (2016)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- model free
- machine learning
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- deep learning
- multi agent
- perceptual aliasing
- website
- learning algorithm
- robotic control
- temporal difference learning
- learning capabilities
- transfer learning
- optimal control
- evolutionary algorithm
- learning process
- case study
- information retrieval