AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Unsupervised Skill Discovery via Recurrent Skill Training

Zheyuan Jiang, Jingyue Gao, Jianyu Chen

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Unsupervised skill discovery · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train skills one after another recurrently with RND-based state coverage reward instead of in parallelReST vs DIAYN/DADS · 2D navigation mazes (DoorMaze, CenterMaze, 4RoomMaze, 9RoomMaze)state coverageImproved
recurrent skill training instead of parallel trainingReST vs DIAYN/DADS · 2D navigation mazesmutual information I(S;Z)No clear effect
use independent neural networks per skill instead of latent-conditioned network in DIAYN and DADS (ablation)DIAYN, DADS · 2D navigation mazesstate coverage and mutual informationNo clear effect
recurrent skill training in place of parallel trainingReST vs DIAYN/DADS · HalfCheetah, Hopper, Walker2dx position over time (semi-quantitative)Improved
train only one skill per epoch instead of all skills in parallelReST · skill discovery trainingsample complexityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy