AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

Jongwook Choi, Archit Sharma, Honglak Lee, Sergey Levine, Shixiang Shane Gu

ICML 2021 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 4 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
Add Posterior HER to DIAYN (ablation)DIAYN · MuJoCo locomotion; large discrete goal spacesLGR(z) accuracy: 0.801 -> 0.844 (HalfCheetah, |G|=200); 0.113 -> 0.263 (Ant, |G|=200); 0.337 -> 0.766 (Humanoid, |G|=200)Improved
Add Posterior HER to DIAYN (ablation)DIAYN · MuJoCo locomotion, |G|=10–1000LGR(z) accuracy: HalfCheetah, |G|=10: 0.963 -> 0.934; Ant, |G|=10: 0.806 -> 0.889Mixed
Add spectral normalization to the discriminator (ablation)DIAYN · 2D PointMass, |G|=10 and |G|=20LGR(z): 0.94 -> 0.96; 0.91 -> 0.96Improved
Add spectral normalization to the discriminator (ablation)DIAYN · 2D PointMass, |G|=50LGR(z): 0.83 -> 0.78Hurt
Learn a global adaptive covariance instead of fixing the goal-reward variance (ablation)GCRL · Windy PointMassgoal-reaching performance in controllable dimensionImproved
Use a linear learned mapping from observations to latent goals (ablation)GCRL · 2D PointMass with random linear observation projectionrecovery of intrinsic dimensionsImproved
Add spectral normalization to a Gaussian discriminator (ablation)VGCRL-Gaussian · MuJoCo locomotionLGR(z)Improved

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