Experience Replay Buffer for Multiple Processing `int max_len` the max_len of ReplayBuffer, not the total len of ReplayBufferMP `int worker_num` the rollout workers number
(self, max_len, worker_num,
state_dim, action_dim, if_discrete, if_on_policy, if_per_or_gae)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected