DontGiveUpEasily

Results 4 issues of


                                            DontGiveUpEasily

why is DDPG so unstable?

2

comment

I can train a good agent, but the learning curve is quite noisy. why? is it an implementation issue or something intrinsic to DDPG?

are you able to get the global map of vizdoom?

I'm wondering if the top view map is available?

does not work for python3.6

I tried to install this with anaconda 3.6, but didn't work

where is the function corresponding to calculating the KL divergence between p(z|x) and p(z)?

As titled.