"Noisy TV problem" is solvable by introducing yet another level of abstraction :)
Curiosity-Driven Exploration via Latent Bayesian Surprise
https://arxiv.org/abs/2104.07495
More on the topic: https://lilianweng.github.io/posts/2020-06-07-exploration-drl/
Post #792
173
- 🤔 3