It’s not the same (but similar), because my proposal is just about learning a model of impact, and has nothing to do with the agent’s utility function.
You could use the learned impact function, I, to help measure (and penalize) impact, however.
It’s not the same (but similar), because my proposal is just about learning a model of impact, and has nothing to do with the agent’s utility function.
You could use the learned impact function, I, to help measure (and penalize) impact, however.