search

zuoxingdong / lagom

lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.
MIT License
373 stars 30 forks source link

Agent.choose_action: replace the mode string argument with internal self.training #211

Open zuoxingdong opened 4 years ago

zuoxingdong commented 4 years ago

Sync. RL baselines by calling agent.train() and agent.eval() explicitly.