Open cpnota opened 3 years ago
@cpnota
One thing blocking this is that several internal features, including the generalized advantage buffer used by PPO, only work for parallel agents. And there is no parallel multiagent experiment.
Good to know. Will probably have to do some additional changes. Have you tried SAC/DDPG?
Blocked on #219 for now
Add multiagent presets for the Butterfly continuous environments.