Top stable-baselines issues

Dueling and Double DQN

enhancement question
edwinlima picture edwinlima·15 Jul 2019·1 Comments
👍2

Choice of Q value in the policy loss of SAC algorithm

question
maximeLR picture maximeLR·14 May 2019·5 Comments

Mean Episode Reward and Length showing NaN in PPO2 training.

enhancement good first issue help wanted
batu picture batu·18 Sep 2018·10 Comments
👍3

Upgrade to Tensorflow 2

enhancement question
iirekm picture iirekm·27 Sep 2020·6 Comments
👍1

AttributeError: 'NoneType' object has no attribute 'get'

custom gym env more information needed
chyunf001 picture chyunf001·6 Jul 2020·6 Comments

[question] Training sequential tasks on multiple instances of an environment

question
mhtb32 picture mhtb32·7 Jun 2020·5 Comments

[Question] Callback for GAIL

bug
prabhasak picture prabhasak·26 Apr 2020·16 Comments

Reverse sign in TD-error of DQN

enhancement
juliuskittler picture juliuskittler·16 Apr 2020·4 Comments

When using HER + SAC, every call to learn massively decreases performance

bug
siferati picture siferati·9 Mar 2020·6 Comments

DQN output is normalized?

RTFM question
QuXinghuaNTU picture QuXinghuaNTU·24 Feb 2020·4 Comments
 Previous issues
Next issues