From the source
From the source
Decision Transformer (DT) and Generalized DT, which reformulate reinforcement learning as a sequence modeling problem using a transformer architecture, enabling stable policy learning via supervised learning without temporal difference learning.
From the source
In the field of offline RL, a new paradigm called Decision Transformer (DT) was proposed in June of last year. In DT, the reinforcement learning problem was solved by transforming it into a problem commonly encountered in NLP — sequence modeling.
lgresearch.ai
