06f1fd69a6
2.6 KiB
This model was published in HF papers on 2021-06-02 and contributed to Hugging Face Transformers on 2022-03-23.
Decision Transformer
Overview
The Decision Transformer model was proposed in Decision Transformer: Reinforcement Learning via Sequence Modeling
by Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch.
The abstract from the paper is the following:
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.
This version of the model is for tasks where the state is a vector.
This model was contributed by edbeeching. The original code can be found here.
DecisionTransformerConfig
autodoc DecisionTransformerConfig
DecisionTransformerGPT2Model
autodoc DecisionTransformerGPT2Model - forward
DecisionTransformerModel
autodoc DecisionTransformerModel - forward