question about reply buffer size in MAPPO

[Gloriabhsfer]

Thank you for your contribution to the RL community. I have some questions about the reply buffer setting in both shared and separated buffer settings. When I am training, I don't want parallel env, so my num_rollout_thread is 1, and the buffer_size is batch_size = n_rollout_threads * episode_length * num_agents . in my understanding, this will only keep 1 traj in buffer so my training ratio is always around 1. if I want to enlarge my batch_size, I should set the n_rollout_threads be same to the buffer_size that I want ?