ALP-GMM
Absolute Learning Progress and Gaussian Mixture Models for Automatic Curriculum Learning
2000년 도입 · 논문 1편에서 사용
ALP-GMM is is an algorithm that learns to generate a learning curriculum for black box reinforcement learning agents, whereby it sequentially samples parameters controlling a stochastic procedural generation of tasks or environments.
출처: Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
소개 논문: Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
Self-Supervised Learning · General