flow
flow copied to clipboard
flow-project
Add an implementation of "Learning Multi-agent Communication with Backpropagation" to Flow
It would be interesting to port a few basic communication environments/training procedures to Flow. In particular, a popular communications baselines is "Learning Multi-agent Communication with Backpropagation" (https://arxiv.org/abs/1605.07736). As a request for research, we'd appreciate it if someone added the training procedure from this paper to our codebase. For open source reproductions of the training process, you can look here: https://github.com/KornbergFresnel/CommNet
To be clearer what would be great is: (1) Take any of our existing environments, add vehicle to vehicle communication to them as part of the action space. (2) Add a script to train in the new environment and use the Commnet as the model.
Hi Eugene, I'm interested in contributing to this feature request. Would I be able to be an assignee for this feature?
Hi Eugene, I've noticed that we currently use ray.rllib for the reinforcement learning algorithm. Do you suggest implementing CommNet from scratch to replace the existing RL algorithms supported by ray.rllib?
Hi Jenna, So in this case of the CommNet, there isn't an algorithmic change, it's just a model. So you would just need to implement the model; the actual construction of a policy gradient would just be handled by rllib.
Excellent, I will probably work on that since I definitely need to add some communication between my agents. I was also thinking on implementing the model proposed in "Connectivity-driven Communication in Multi-agent Reinforcement Learning through Diffusion Processes on Graphs". I will keep you in-the-loop. Thanks.
Please! We'd love any implementation you have, I've been meaning to play around with communication in these environments for YEARS.
