Ian Osband

Hi David - looks like there is something wrong with this pull request... I'm having a look if this improves performance

I had a look at this change locally and within Google and I don't think I saw a benefit... bit confused what's going on here

Hi Aaron! Apologies for the delay in getting back here... we can try and add some more documentation about where this comes from. In each experiment/sweep.py there is a list...

Hi Peter! Thanks for raising this... I think we might have seen some slippage in agent performance. I'm not sure if this has come from updates to: - Tensorflow 1...

Hello again! I have just run the agents checked in at HEAD and I did not see your observed scoring...  We may need to tool in some more continuous...

Yes @mklissa - I see that difference above. There have been several moving pieces: - Changes to the bsuite environment (at release MountainCar had gravity the wrong direction) - Changes...

Ah... OK well I think in order to get the claimed performance, you need to run the dqn.default_agent() I can see that this is a bit confusing, but we wanted...

Hi @jbarsce - I'm not sure I understand the question. So, are you saying that: (a) The TF DQN checked into bsuite.baselines is not solving the bandit task for you?...

 For reference, here is a record of the nightly runs for the TF baselines. You can see that some of the experiments are a little noisy... but that the...

Yes interesting... something is getting lost between the version that is checked in to Google3 and the settings you are running. @yotam @aslanides and I will have a look into...