search

hongzimao / pensieve

Neural Adaptive Video Streaming with Pensieve (SIGCOMM '17)
http://web.mit.edu/pensieve/
MIT License
517 stars 280 forks source link

Training with Multiple videos with random number of bitrates masked. #99

Open manojsoni2 opened 4 years ago

manojsoni2 commented 4 years ago

We are trying to train this model for multiple video using PPO with different masks(variable number of bit rates masked). For example, there are currently maximum 12 bitrates and some of them are randomly masked in different videos. Some times there are only 9 of them available and some time only 6 and so on.

So far we are trying to use the same dataset as used for A3C. But in our approach there seems to be issues in experience batch creation and its further processing. Can you share a reference how to create a video data set for PPO with different masks.

hongzimao commented 4 years ago

The masking mechanism is https://github.com/hongzimao/pensieve/blob/master/multi_video_sim/a3c.py#L90-L95. We didn't train PPO in our experiment though.

Now that you talk about agent design to support variable number of video encoding, I would suggest you take a look at Figure 3 and section 3.2 Policy of https://openreview.net/forum?id=SJlCkwN8iV. It's using a more principled way than masking to support arbitrary number of bitrate levels.