Is it possible to change the number of workers during training?

Luana_Martins January 6, 2021, 9:38pm 1

During DQN training, it is possible to configure a certain number of workers to fill in the replay_buffer until reaching learning_starts, and after that decrease the number of workers?

Topic		Replies	Views
Lowering the number of episodes per training iteration during tune.run RLlib	2	458	May 12, 2021
DQN (and maybe other algo) should take into account the "num_envs_per_worker" config when computing the round robin native_ratio used to determined the number of steps to use for training RLlib	3	548	April 21, 2021
Understanding the Stopping Process for ray.rllib.agents.dqn.DQNTrainer.train() RLlib	4	662	May 26, 2021
Training steps for DQN Configure Algorithm, Training, Evaluation, Scaling	3	181	April 18, 2024
DQNTrainer evaluate() doesn't perform any episode RLlib	1	538	March 16, 2022

Is it possible to change the number of workers during training?

Related topics