The result is not that ideal like the paper showed

[Jarvis]

I just run maddpg in simple_speaker_listener several times,but none of them get the -20 avg-reward like the paper proposed. Are there anything i should modify to get a better or more stable result?

[Agor Maxime]

Looks like you're not the only one having trouble reproducing some results: #12

[Bolun Dai]

I am getting -60 rewards, is that normal for just running the code without any alternations?

[Ken]

Also, in scenario=simple_speaker_listener, this code cannot converge to the result reported in Fig.4. Anyone knows the problem?