Multi-vehicle collaborative boxing method based on sequence-to-sequence strategy network deep reinforcement learning model

According to the method, the cargo loading sequence problem in the multi-vehicle collaborative boxing problem under the logistics loading scene with only the rear container door is researched, and the utilization rate of the vehicle loading space is determined. On the basis of deep reinforcement learning, firstly, a sequence model based on a Seq2Seq network is constructed, and the model respectively constructs an encoder, a decoder and an attention module by combining a bidirectional LSTM model and an attention mechanism, so that the loading probability of all articles to be loaded is obtained. And then, obtaining an article loading strategy through the constructed deep reinforcement learning encasement framework, updating and optimizing the Seq2Seq strategy network by a strategy gradient method with a baseline, and finally obtaining an optimal loading strategy. A large number of experiments prove that compared with previous research, the method has the advantages that both the space utilization rate and the