Learning to multi-vehicle cooperative bin packing problem via sequence-to-sequence policy network with deep reinforcement learning model.
Ran TianChunming KangJiaming BiZhongyu MaYanxing LiuSaisai YangFangfang LiPublished in: Comput. Ind. Eng. (2023)
Keyphrases
- reinforcement learning
- hidden state
- cooperative
- prior knowledge
- learning algorithm
- network model
- learning process
- probabilistic model
- partially observable
- hidden markov models
- wireless sensor networks
- supervised learning
- peer to peer
- optimal policy
- network structure
- learning tasks
- connectionist networks
- learning models
- lower bound
- neural network
- multilayer neural network
- policy gradient
- fully connected
- function approximation
- multi agent
- machine learning