matheusportela / Multiagent-RL

Multiagent reinforcement learning simulation framework - Undergraduate thesis in Mechatronics Engineering at the University of Brasília
67 stars 16 forks source link

Execute agent action selection in different threads #71

Closed matheusportela closed 1 year ago

matheusportela commented 7 years ago

Now, controller is one single-thread process which has to handle action selection for all agents. Probably, multithreading will make it be faster (although Python's GIL may reduce gains).