cogment / cogment-verse

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
https://cogment.ai/cogment_verse
Apache License 2.0
78 stars 14 forks source link

Fix multiple actions per timestep #30

Closed jmf1sh closed 2 years ago

jmf1sh commented 2 years ago

PR fixes an issue where the webclient sends actions multiple times per timestep. Functionally there is no difference since the orchestrator ignores all actions but the first.