pymarl
Python Multi-Agent Reinforcement Learning framework (by oxwhirl)
maddpg
Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" (by openai)
Our great sponsors
pymarl | maddpg | |
---|---|---|
3 | 2 | |
1,679 | 1,521 | |
5.2% | 4.2% | |
0.0 | 0.0 | |
over 1 year ago | 25 days ago | |
Python | Python | |
Apache License 2.0 | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pymarl
Posts with mentions or reviews of pymarl.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-02-15.
-
Centralized-Learning Distributed-Execution for Multi Agent RL using SB3
Not directly, but you can modify it to allow the critic to receive the observations from the other agents, but it will be better to use other libraries such as RLLib or Pymarl
-
How to build QMIX agent network?
Hi, are you aware that the authors have open-sourced their code here: https://github.com/oxwhirl/pymarl? For the RNN agent, please see the agent.py file within src.modules.agents. To see how they process their input, you can check the _build_inputs method within their basic_controller.py file.
-
How to get my multi-agents more collaborative?
Cooperative agents is a research field on its own. Check out some recent papers like QMIX, paper linked in this repo: https://github.com/oxwhirl/pymarl/
maddpg
Posts with mentions or reviews of maddpg.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-02-15.
-
How is the backward pass performed in MADDPG algorithm from MARL
I'm using the MADDPG algorithm from https://github.com/openai/maddpg/blob/master/maddpg/trainer/maddpg.py. I understood the forward pass for both the actor and critic networks. I'm not able to understand how the actor and critic networks are updates. Like at line 188 and 191 the authors compute the critic loss and actor loss. But can anyone explain how the critic and actor networks are updated. Also, as far as I understand, when the number of agents increases from 3 to 6 for a simple spread policy in MADDPG, the computation time for Q loss and P loss at lines 188 and 191 increase super-linearly. I'm assuming this might be because both the Q loss and P loss utilize the Q values and the dimension to calculate the Q values increases with the number of increasing linearly. It would be great if anyone can help me to understand this back propagation phase much better and why does the computation time grow super-linearly. I also put a time counter to track the computation time of Q loss and P loss for 60,000 episodes with simple spread policy (3 agents, 3 landmarks, 0 adversaries). Thanks for the help, in advance! **Q loss** 3 agents 74.31 sec 6 agents 243.31 sec (3X) **P loss** 3 agents 114.86 sec 6 agents 321.76 sec (3x)
-
How to get my multi-agents more collaborative?
Another thing is that I don't use only one centralized critic, I'm using one for each agent (they are all centralized), you could use parameter sharing for the ones of the same type if you want. A great start would be to look at how the MADDPG works in an implementation (original, tf2 ,pytorch-1 , pytorch-2 ), then you can see how it is the training of the actor and the critic and just adapt the ideas to your MA-PPO implementation.
What are some alternatives?
When comparing pymarl and maddpg you can also consider the following projects:
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
multiagent-particle-envs - Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
transferlearning - Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习