Deep Reinforcement Learning with Swin Transformer. (arXiv:2206.15269v1 [cs.LG])

Transformers are neural network models that utilize multiple layers of
self-attention heads. Attention is implemented in transformers as the
contextual embeddings of the 'key' and 'query'. Transformers allow the
re-combination of attention information from different layers and the
processing of all inputs at once, which are more convenient than recurrent
neural networks when dealt with a large number of data. Transformers have
exhibited great performances on natural language processing tasks in recent
years. Meanwhile, there have been tremendous efforts to …

arxiv learning lg reinforcement reinforcement learning swin transformer