kzl/decision-transformer

• hightopics#1

  Add relevant topics to the repository

  Why:

  COPY-PASTE FIX

  Copy

  reinforcement-learning, offline-rl, sequence-modeling, transformers, deep-learning, machine-learning, atari, openai-gym

  OpenDoneDismiss
• highreadme#2

  Clarify the README's opening to emphasize Decision Transformer as a specific RL method

  Why:

  CURRENT

  # Decision Transformer
  
  Lili Chen*, Kevin Lu*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas†, and Igor Mordatch†
  
  *equal contribution, †equal advising
  
  A link to our paper can be found on arXiv.
  
  ## Overview
  
  Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

  COPY-PASTE FIX

  Copy

  # Decision Transformer: Reinforcement Learning via Sequence Modeling
  
  This repository provides the official codebase for **Decision Transformer**, a novel approach that reframes reinforcement learning as a sequence modeling problem. It enables offline reinforcement learning by predicting actions conditioned on desired future returns, past states, and past actions, leveraging the power of Transformer architectures.
  
  Lili Chen*, Kevin Lu*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas†, and Igor Mordatch†
  
  *equal contribution, †equal advising
  
  A link to our paper can be found on arXiv.
  
  ## Overview
  
  Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

  OpenDoneDismiss
• mediumhomepage#3

  Add the arXiv paper link as the repository homepage

  Why:

  COPY-PASTE FIX

  Copy

  https://arxiv.org/abs/2106.01345

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  How can I apply sequence modeling to solve reinforcement learning tasks effectively?

  you: not recommended
  AI recommended (in order):

  1. Hugging Face Transformers library (huggingface/transformers)
  2. minGPT (karpathy/minGPT)
  3. PyTorch (pytorch/pytorch)
  4. TensorFlow Keras (tensorflow/tensorflow)
  5. PyTorch Geometric (PyG) (pyg-team/pytorch_geometric)
  6. Deep Graph Library (DGL) (dmlc/dgl)

  AI recommended 6 alternatives but never named kzl/decision-transformer. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  What are the best methods for offline reinforcement learning without explicit policy optimization?

  you: not recommended
  AI recommended (in order):

  1. Behavior Cloning (BC)
  2. Imitation Learning from Observations (ILO)
  3. Inverse Reinforcement Learning (IRL)
  4. Generative Adversarial Imitation Learning (GAIL)
  5. Dataset Aggregation (DAgger)
  6. Variational Discriminator Bottleneck (VDB)

  AI recommended 6 alternatives but never named kzl/decision-transformer. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of kzl/decision-transformer?

  pass
  ⚠AI did not name kzl/decision-transformer — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts kzl/decision-transformer in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named kzl/decision-transformer explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo kzl/decision-transformer solve, and who is the primary audience?

  pass
  ✓AI named kzl/decision-transformer explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?