is it really a3c implementation? not just actor critic?

[sevity]

where is multi-step loss function and entropy loss function?

[KGBUSH]

where is multi-step loss function and entropy loss function?

For entropy exploration, you can check continuous_A3C.py in loss_func function

[jakkarn]

This should be the if-condition that determines when N actions have been taken (or terminated) in the Worker:

pytorch-A3C/discrete_A3C.py

Line 93 in 5ab27ab

if total_step % UPDATE_GLOBAL_ITER == 0 or done: # update global and assign to local net

N-step loss is then computed in push_and_pull in this loop:

pytorch-A3C/utils.py

Line 29 in 5ab27ab

for r in br[::-1]: # reverse buffer r