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

openai / maddpg

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

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

MIT License

1.66k stars 494 forks source link

How to normalize the data in table of Appendix to obtain Figure 3 in paper? #55

Open flammingRaven opened 3 years ago

flammingRaven commented 3 years ago

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!

Vivian0322 commented 3 years ago

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