Jiarong Liu

Hi. Your idea is very interesting. Combining transformer with HARL algorithms indeed has the potential to further improve performance. Your idea is similar to the paper ["Multi-Agent Reinforcement Learning is...

Hi. This problem might be caused by improper hyperparameter settings. You can try using the hyperparameters in the "tuned_configs" first. If the problem persists, it might be due to the...

Hello, I find the issue you've discovered very interesting. Could you provide more detailed information? For example, which algorithm are you using and how are the hyperparameters set? This will...

Hello. Reproducing our experiments does not require massive computational resources. A single 3090 GPU is sufficient. Experiments on SMAC typically take a few hours to complete, with off-policy algorithms potentially...