The success of DQN explained by “shallow” reinforcement learning (amii.ca)

2 points by yamaneko 9y ago ↗ HN

0 comments

[ 8.1 ms ] story [ 10.1 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats