Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

Source: Deep Learning on Medium

Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

teacher (multi-armed Bandit) / student (POMDP) curriculum learning

interesting for correspondence to cognitive science and rich mixture of empirical tests (RL, LSTMs, human children (?!?!) )

https://arxiv.org/pdf/1910.07224.pdf