Open jafermarq opened 1 year ago
Hi @jafermarq
This is the contribution plan I'd like to propose:
gymnasium
into flower
for conducting Federated Reinforcement Learning experiments
flower
, which I think would be interesting and challengingLet me know your thoughts and yes, I am eligible for the reward.
Cheers, Flint
Hi @flint-xf-fan, thanks for getting back to us with this detailed plan. Reproducing the results in Figure 2 sounds good. I'll look into how integrating OpenAi's gymnasium
can be done with how Flower
's server <--> client interactions work. Please give me a couple of days and i'll get back to you regarding this. I'll β
some the points above in the description of the issue and add you as assignee.
Hi @flint-xf-fan , after looking into your paper more closely: wouldn't it be sufficient if all clients and the server have their own gym
instantiation? Then, the clients sample a batch of trajectories independently, obtain gradients and communicate them to the server. Most examples in Flower show how to send the entire model back to the server, but adjusting it to instead communicate the gradients isn't difficult (it just requires adjusting the get_parameters()
method in the flower clients). Then the server updates the policy. My understanding is that the server does also need a gym
instance to do line 11 in Algo1.
If having multiple gym
instances is a problem (maybe due to compute/memory resources needed to support that), we could think of alternatives.
Hi @jafermarq, that sounds the right approach. I have gone through some tutorials on Flower, and I would like to start the implementation, as you suggested:
Hi @jafermarq I am another author of FedPG-BR and am working with @flint-xf-fan on this. We are planing to submit the PR by end of this week. Can you add me as contributor to this issue?
It's great to have you on board also @yining043 ! You are now a contributor.
FedPG-BR
Do you want to work on this baseline?
What follows are the steps 1 & 2 in the Summer of Reproducibility instructions.
1. Join the Summer of Reproducibility program
#summer-of-reproducibility
.2. Define the scope of your contribution
[x] Check if you are eligible for a reward.
If where you are based is not on the list, please send us an email (
summer@flower.dev
) letting us know a bit about yourself (where are you currently based?, are you a university student? do you work at a public institution?). Please tell us the baselines you are interested in implementing (i.e. tell us your GitHub issue if you have crated one). We will reach back to you.What happens next?
[ ] This item will be moved to the
In Progress
stage by a member of the Flower Team.[ ] Follow the instructions for creating a new baseline which will guide you through the process step-by-step.
Is something wrong or not clear ?