search

hongzimao / pensieve

Neural Adaptive Video Streaming with Pensieve (SIGCOMM '17)
http://web.mit.edu/pensieve/
MIT License
516 stars 279 forks source link

Linear reward #118

Open ali1hammoud opened 3 years ago

ali1hammoud commented 3 years ago

https://github.com/hongzimao/pensieve/blob/1120bb173958dc9bc9f2ebff1a8fe688b6f4e93c/sim/multi_agent.py#L245

Can you explain to me, how did we choose this equation?

hongzimao commented 3 years ago

It's directly derived from the objective we want to optimize for (equation 6 of the paper). The objective was just a standard metric prior work agreed on (see reference 51 of the paper).