-
-
Hi all,
I started using `ray` for a reinforcement learning project I am working on, and it's a fantastic library! However, I've run into a (probably very niche) design issue and was wondering if so…
-
Hi, I've been reading through the code and found that the NRNNAgent(from n_rnn_agent.py) has almost negligible differences from the RNNAgent(from rnn_agent.py). The same goes between the BasicMAC(basi…
-
for 7m-5m-3m transfer learning，when I use the updet model combined with qmix，there is a dimension mismatch problem.
Only the updet model combined with VDN support transfer learning?
-
-
- Examples are a bit messy, we need to reduce the number of examples and only keep the useful ones.
- Fix old qmix examples.
- For networks - check all examples use adequate networks (**specifica…
-
https://arxiv.org/abs/2103.11883v1
-
您好，请问你们复现结果中的wqmix是OW_qmix 还是CW_qmix呢？我运行了ow_qmix的方法在corridor场景中效果非常差，胜率一直为零。
-
I just fetched `master` and started Builder, and the Pump Component seems to have disappeared from the Components panel. It ought to appear under `Custom`.
-
In the experiments of LICA, env steps are set to be 32 or 64 million steps.
In the experiments of QMIX, env steps are set to be 1 to 3 million steps.
Why the env steps are quite different? I don't …