openai / coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"
https://blog.openai.com/quantifying-generalization-in-reinforcement-learning/
MIT License
388 stars 87 forks source link

Variable envsperbatch is assigned twice #5

Closed saschaschramm closed 5 years ago

saschaschramm commented 5 years ago
envsperbatch = nenvs // nminibatches
 ...
envsperbatch = nbatch_train // insteps