Dueling Network Architectures for Deep Reinforcement Learning.
Ziyu WangNando de FreitasMarc LanctotPublished in: CoRR (2015)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference learning
- multi agent
- temporal difference
- model free
- learning process
- state space
- supervised learning
- optimal policy
- markov decision processes
- machine learning
- optimal control
- search algorithm
- learning capabilities
- multi agent reinforcement learning
- robotic control
- website
- decision making
- artificial intelligence
- information retrieval
- partially observable markov decision processes
- deep learning
- databases
- reinforcement learning methods
- continuous state
- relational reinforcement learning