But you could design training runs that include agents with very different amounts of compute and see how stable the pro-social behavior is. You could also try to determine how instinct parameters have to be tuned to keep the pro-social behavior stable.
But you could design training runs that include agents with very different amounts of compute and see how stable the pro-social behavior is. You could also try to determine how instinct parameters have to be tuned to keep the pro-social behavior stable.