Self-Supervised Learning

Absolute Learning Progress and Gaussian Mixture Models for Automatic Curriculum Learning

Introduced by Portelas et al. in Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

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.

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

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Curriculum Learning 1 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories