Does the DQN fall in the paradigm of decentralized training and decentralized execution.

geek-ai / MAgent

A Platform for Many-Agent Reinforcement Learning

MIT License

1.68k stars 332 forks source link

Does the DQN fall in the paradigm of decentralized training and decentralized execution. #78

Open lml519 opened 4 years ago

lml519 commented 4 years ago

Does the DQN fall in the paradigm of decentralized training and decentralized execution. I think it is the alogorithm to combine the Parallel computing with the DTDE. I'm not sure if my idea is right

merrymercy commented 4 years ago

I believe our DQN is in the paradigm of centralized training and decentralized execution. During training, we collect all trajectories and train a single shared model, so the training is centralized. During inference, we feed in different observations and agent embeddings, so the execution is decentralized.