Decision Transformer: Reinforcement Learning via Sequence Modeling
This provides a simpler, scalable approach to reinforcement learning for AI researchers, though it is incremental in leveraging existing Transformer architectures.
The authors tackled reinforcement learning by reframing it as a sequence modeling problem, resulting in Decision Transformer, which matches or exceeds state-of-the-art model-free offline RL performance on tasks like Atari and OpenAI Gym.
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 language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.