Decision Transformer

RL tasks can be solved with transformer sequence modelling

• Compute
  Reward to Go and train trajectory

• Return conditioned policy can be used for policy rollout

1. desired return $R_0$

2. subtract reward

• More supervision and MDP can be differ per task

Decision Transformer: Reinforcement Learning via Sequence Modeling

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in…

https://ar5iv.labs.arxiv.org/html/2106.01345