openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Home Page:https://arxiv.org/pdf/1706.02275.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to normalize the data in table of Appendix to obtain Figure 3 in paper?

flammingRaven opened this issue · comments

Dear Author,

I am replicating your results recently, and a little confused about Figure 3 in the paper, how the data, specifically the in the table of Appendix (e.g. success rate of agents, adversaries in Table 4) can be normalized to get that 'histogram'. Now I think that if that normalized value is computed referred to the maximum value of one column? or what is exactly the score of an agent? Please give me some hints.

Thank you in advance sincerely!

image

hi,have you ever find the answer?i also want to know what the agent score is