SQDDPG
SQDDPG copied to clipboard
hsvgbkhgbv
This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Global R...
When I run test.py, or run source test.sh, there is a mistake: 'MultiAgentEnv' object has no attribute 'name' This happens particularly when I add the argument render.
Typical usage: python train.py --nprocesses 2
Deer author, have you do some tests about continuous actions space envs? Can i let 'continuous=True'? After i use continuous actions space envs to test, it shows that 'action_optimizer.param_groups[0]['params']' no...
Hi, Thanks for the implementation and wonderful work. I was trying to run the IDDPG with a simple tag and trying to observe the result. Can you help me understand...
Metadata
Owner
Metadata
This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Global R...