balintkozma
balintkozma
The root cause of this problem can be related to this: `total_episode_reward_logger` is "borrowed" from the A2C module, and used incorrectly in PPO2. It calculates the step counter of the...
@Miffyli I created the PR, meanwhile I found another problem: If a shorter episode is added to the episode reward summary after a longer one, the graph will go backwards,...
It works if I specify my own preinst file, yes. The template is wrong anyway imo, but there is a workaround, at least. The issue can be closed.