AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Patrik Reizinger, Bálint Mucsányi, Siyuan Guo, Benjamin Eysenbach, Bernhard Schölkopf, Wieland Brendel

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations

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 a small fixed set of pre-sampled skills instead of sampling skills from the uniform prior (ablation)CSF · Ant (MuJoCo)state coverage and R2 of linear fit to ground-truth stateHurt
increase the number of fixed discrete skills (enough to span the state space) (ablation)CSF · Ant (MuJoCo)R2 / zero-shot oracle rewardImproved
use a latent dimensionality smaller than the ground-truth state dimensionality (ablation)CSF · Ant (MuJoCo)R2 (state identifiability)Hurt
use a smaller latent dimensionality for zero-shot task transfer (ablation)CSF · Ant (MuJoCo)oracle reward (zero-shot transfer)Mixed
match latent dimensionality to the ground-truth state dimensionality (ablation)CSF · Ant (MuJoCo)R2 (state identifiability)Improved
train CSF from states rather than pixelsCSF · Half Cheetah, Ant, Quadruped (state) vs Quadruped (pixel)R2 of linear fit to ground-truth stateImproved
increase the number of negative samples in the contrastive loss (ablation)CSF · MuJoCo/DMC environmentsstate coverage and oracle rewardMixed
add skip-connections to the encoder backboneCSF · MuJoCo/DMC environmentsidentifiabilityNo clear effect
use a maximum-entropy skill-conditioned policyCSF · theory (Lemma)skill diversity / rewardHurt
optimize I(s;z) instead of I(s,s';z)CSF · theoryfeature geometryHurt

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