feature(rjy): add smac env #171
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
puyuan1996
requested changes
Dec 22, 2023
zoo/smac/utils/eval.py
Outdated
| path = '../exp/MMM/qmix/1/ckpt_BaseLearner_Wed_Jul_14_22_16_56_2021/iteration_9900.pth.tar' | ||
| cfg = '../config/smac_MMM_qmix_config.py' | ||
| state_dict = torch.load(path, map_location='cpu') | ||
| eval(cfg, seed=0, state_dict=state_dict) |
There was a problem hiding this comment.
在安装好SMAC后，需要保证这里给出的eval是可运行的，并且可以存储replay的gif或者MP4文件
There was a problem hiding this comment.
这里是之前diengine的，我先删掉，后续lz pipeline可以收敛有ckpt后再增加这个eval文件
| @@ -0,0 +1,7 @@ | |||
| import warnings | |||
There was a problem hiding this comment.
增加一下SMAC 在 SEZ/EZ independent learning 上的可运行config
puyuan1996
added
environment
puyuan1996
requested changes
Jun 12, 2024
| @@ -0,0 +1,58 @@ | |||
| ## PYSC2 Env | |||
| SMAC (StarCraft Multi-Agent Challenge) is an environment used for multi-agent reinforcement learning research based on the popular real-time strategy game StarCraft II. It provides a suite of tasks where agents need to cooperate to achieve specific objectives. This environment is widely used to benchmark the performance of multi-agent learning algorithms. LightZero use modified pysc2 env (for more maps and agent vs agent training). | |||
|
|
|||
| 1. **Install StarCraft II:** | ||
| ```bash | ||
| # Create a conda environment | ||
| conda create -n ace python=3.8 |
There was a problem hiding this comment.
ace 换成 lightzero-smac ?
| 2. **Install dependencies:** | ||
| ```bash | ||
| # Install PySC2 and Protobuf | ||
| pip install pysc2 protobuf==3.19.5 |
There was a problem hiding this comment.
我的mac本地protobuf==3.20.0测试的报错少一些，你保证按照这里的方式能成功通过测试就好哈
|
|
||
| 2. **Run the tests using pytest:** | ||
| ```bash | ||
| pytest test_smac_env.py |
| @@ -0,0 +1,15 @@ | |||
| # Notes on Two Player Maps | |||
|
|
|||
| Before starting, you need to do the following things: | |||
There was a problem hiding this comment.
Two Player Maps具体相对SMAC_Maps的区别是什么？这个文档更新一下吧
zoo/smac/envs/test_smac_env.py
Outdated
| @pytest.mark.envtest | ||
| class TestSmacEnv: | ||
|
|
||
| def test_samc(): |
| import os | ||
|
|
||
|
|
||
| class SMACMap(lib.Map): |
There was a problem hiding this comment.
这个和DI-engine里面的一样吗？如果一样import就可以哈
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Description
This PR introduces the SMAC (StarCraft Multi-Agent Challenge) environment to the LightZero repository. The included environment is fully operational and has been tested for functionality. However, please note that there are currently no matching pipelines available for this environment within the repository. Future updates will include the necessary pipelines to fully integrate SMAC with LightZero.
Key Points:
Next Steps:
Thank you for reviewing this PR. Please feel free to provide any feedback or suggestions for improvements.