Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning.
Fan ZhouZhoufan ZhuQi KuangLiwen ZhangPublished in: IJCAI (2021)
Keyphrases
- reinforcement learning
- network structure
- network model
- peer to peer
- network traffic
- machine learning
- learning algorithm
- network management
- complex networks
- distributed network
- network topologies
- model free
- function approximation
- computer networks
- learning process
- objective function
- web services
- data sets
- optimal policy
- wireless sensor networks
- network architecture
- piecewise linear
- markov decision process
- neural network