Open williamjshipman opened 5 years ago
@williamjshipman It's likely because the code was refactored after the DDPG update, except DDPG wasn't entirely updated with it. Somewhat related to https://github.com/openai/baselines/issues/938 since it showed that there are two normalizations happening for DDPG.
Is there any reason that DDPG doesn't have a load_path parameter like A2C that allows restoring trained weights? I'm adding it in my own copy of the code but was wondering if there's some known problem with doing that.