AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning

Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo, Jan Peters, Joni Pajarinen

JMLR 2021 · Reinforcement learning › Visual and representation RL · approach: Hierarchical skills and priors · 11 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
use V_LB performance-threshold alpha schedule instead of K_alpha/zeta (ablation)SPDL · Point-mass 3D (PPO)iterations to reach threshold: 165 ± 14 -> 120 ± 10Improved
use V_LB alpha schedule instead of K_alpha/zeta (ablation)SPDL · Point-mass 3D (SAC)iterations to reach threshold: 94 ± 8 -> 67 ± 4Improved
use V_LB alpha schedule instead of K_alpha/zeta (ablation)SPDL · Point-mass 2D (SAC)iterations to reach threshold: 134 ± 30 -> 59 ± 3Improved
use V_LB alpha schedule instead of K_alpha/zeta (ablation)SPDL · Ball-catching (SAC)iterations to reach threshold: 205 ± 12 -> 139 ± 8Improved
use V_LB alpha schedule instead of K_alpha/zeta (ablation)SPDL · Ant (PPO)final reward: 1371 ± 23 -> 1305 ± 38No clear effect
use V_LB alpha schedule instead of K_alpha/zeta (ablation)SPDL · Point-mass 2D (SAC)final reward: 5.67 ± 0.77 -> 6.56 ± 0.82No clear effect
increase context dimension from 2D to 3D (add friction)SPDL · Point-mass (PPO)final reward: 8.94 ± 0.10 -> 8.45 ± 0.4No clear effect
increase context dimension from 2D to 3D (add friction)GoalGAN · Point-mass (PPO)final reward: 1.63 ± 0.5 -> 0.66 ± 0.1Hurt
increase context dimension from 2D to 3D (add friction)ALP-GMM · Point-mass (PPO)final reward: 5.23 ± 0.4 -> 2.43 ± 0.3Hurt
initialize context distribution to tasks the initial policy solvesSPDL · Ball-catching (PPO)final reward: 53.9 ± 0.4 -> 49.3 ± 1.4Hurt
initialize context distribution to tasks the initial policy solvesGoalGAN · Ball-catching (PPO)final reward: 42.6 ± 2.7 -> 45.9 ± 1.0Improved
use SPDL curriculum instead of default learning without curriculumPPO · Ball-catchingfinal reward: 22.1 ± 0.3 -> 53.9 ± 0.4Improved

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