Sounds very related to https://towardsdatascience.com/curiosity-in-deep-reinforcement-learning-understanding-random-network-distillation-747b322e2403 , which deals with the problem of RL agents staring at a source of noise because they can’t predict it.
Sounds very related to https://towardsdatascience.com/curiosity-in-deep-reinforcement-learning-understanding-random-network-distillation-747b322e2403 , which deals with the problem of RL agents staring at a source of noise because they can’t predict it.