fixed reward function -> less deflection is rewarding

Browse Source

...

This commit is contained in:

ritchie

2017-12-16 15:26:44 +01:00

parent 599420dbe6

commit c7d6fea511

1 changed files with 80 additions and 111 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

191

reinforcement_learning/her_deep_Q_bridge.ipynb

File diff suppressed because one or more lines are too long