graph_adversarial_attack
graph_adversarial_attack copied to clipboard
Question on the hash_state_action function
https://github.com/Hanjun-Dai/graph_adversarial_attack/blob/57b2853d32e2412dba2c78d10b9a1659954cc49b/code/graph_attack/nstep_replay_mem.py#L54-L66
Is this hash function problematic? It seems that this function is equivalent to key = a_t % base
.