[lab 08] Automatic evaluation of `ddpg.py` InvertedDoublePendulum broken

ufal / npfl139

Materials for Deep Reinforcement Learning – ÚFAL course NPFL139

https://ufal.mff.cuni.cz/courses/npfl139

Creative Commons Attribution Share Alike 4.0 International

8 stars 10 forks source link

[lab 08] Automatic evaluation of `ddpg.py` InvertedDoublePendulum broken #10

Closed paplhjak closed 7 months ago

paplhjak commented 7 months ago

Is it possible that the evaluation of the inverted double pendulum environment is broken? I am receiving returns greater than the specified requirement of 900, but the assignment is evaluated as a failure.

foxik commented 7 months ago

Sorry, my bad, the required level is actually 9000. I just commited a fix 48759a8a5bbb6c95e678e78f0d59aec0575ae1db and another community-work point is yours :+1: