Can I read Decision Transformer for RL via Sequence Modeling on EtoBox?

Decision Transformer for RL via Sequence Modeling by ycdu66 is a document available to read on EtoBox.

What is Decision Transformer for RL via Sequence Modeling about?

The document introduces Decision Transformer, a framework that casts reinforcement learning as a sequence modeling problem that can be solved using a Transformer architecture. Decision Transformer models the joint distribution of states, actions, and rewards to generate optimal future actions conditioned on the desired return, past states, and actions. It matches or exceeds the performance of state-of-the-art offline reinforcement learning baselines on several benchmark tasks despite its simplicity. The key

Author

ycdu66

Language

EN