kzl / decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
MIT License
2.33k stars 440 forks source link

Clarified that return_preds were unnecessary #68

Open nawta opened 8 months ago

nawta commented 8 months ago

I liked your code! It's so easy to re-implement that. and I found that there looks no need to get return_preds in forward method, so I replaced the returnpreds with variable to let people use this code more confidently