Extended Data Fig. 7: Distributed RL training architecture. | Nature

Extended Data Fig. 7: Distributed RL training architecture.

From: Whole-body physics simulation of fruit fly locomotion

Extended Data Fig. 7

Multiple replicas of actors in MuJoCo environments collect experiences and feed them to a single replay buffer. The DMPO learner samples experiences from the replay buffer, updates the policy and critic network weights, and sends the updated weights to the actors’ copies of the policy.

Back to article page