search

chainer / chainerrl

ChainerRL is a deep reinforcement learning library built on top of Chainer.
MIT License
1.17k stars 224 forks source link

Adds proper A3C scores #581

Closed prabhatnagarajan closed 4 years ago

prabhatnagarajan commented 4 years ago

Previously, the A3C results reported the best intermediate score every 1M timesteps. Now it reports the best intermediate score every 250K timesteps.

ummavi commented 4 years ago

/test

pfn-ci-bot commented 4 years ago

Successfully created a job for commit 3ea6b3f: