kzl / decision-transformer

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

Number of training steps #78

Open mhngu23 opened 3 weeks ago

mhngu23 commented 3 weeks ago

Hi,

Thank you for the paper and your code.

I am writing to query about your decision on the number of training steps. Specifically, what is the reason behind choosing 10*10000 steps instead of a higher value, as I believe this will improve the performance in term of accuracy?

Thank you for your attention!