DeepRLHacks icon indicating copy to clipboard operation
DeepRLHacks copied to clipboard

Published 20 hours ago • verified publisher icon williamFalcon
→

Metadata

Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)

Results 1 DeepRLHacks issues
Sort by recently updated
recently updated
newest added

KL divergence : size of update

In the section [Policy Gradients diagnostics](https://github.com/williamFalcon/DeepRLHacks#policy-gradient-diagnostics), it is mentioned : > If KL is .01 then very small. If 10 then too much. I couldn't find the given values in...

astariul avatar astariul

← Metadata

1.1k
Stars
127
Forks
Watchers

Owner

verified publisher icon williamFalcon

Metadata

Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)

Back