HARL
HARL copied to clipboard
PKU-MARL
Official implementation of HARL algorithms based on PyTorch.
Hi, your work is interesting and I hope to replicate and follow your work. But I am worried that my resources are not enough to support this. I hope you...
Thank you for your work first. I'm trying to use your algorithm in my own environment. But I find the distribution entrophy of continues action space always ascends, even in...
Hi, I am interested in your work on heterogeneous-agent reinforcement learning and the algorithms you have developed. I noticed that your current implementation focuses on algorithms like HAPPO, HATRPO, etc.,...
At first, there was no problem, but after 210,000 steps, an error was suddenly reported Looks like the problem is caused by the Normal function，the code is in harl/models/policy_models/squashed_gaussian_policy.py line...
Hi, I have a question about the HASAC. When I run HASAC on smac, it always stuck with "finish warmup, start training". I didn't have this question when I used...
if self.state_type == "EP": data = ( share_obs[:, 0], # (n_threads, share_obs_dim) obs, # (n_agents, n_threads, obs_dim) actions, # (n_agents, n_threads, action_dim) available_actions, # None or (n_agents, n_threads, action_number) rewards[:,...
Hello, Thank you for sharing your code, it has been incredibly useful! I am currently trying to use your MAPPO or HAPPO to run my tasks where my actions are...
I'm using the hasac algorithm for my own environment, and the reward oscillates, what could be the cause?
I noticed that with on policy algorithms, the data collection process is done in the `run` function in `OnPolicyBaseRunner`. However, in my experiments, I noticed that my environment would not...
