Transformers, GPT, Reinforcement learning
(Chen et al. 2021)
This is a decoder model that uses a GPT-like model to encode and predict trajectories for Reinforcement learning tasks. It has essentially the same characteristics as GPT.
Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch. . "Decision Transformer: Reinforcement Learning via Sequence Modeling". arXiv. DOI.