AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs

Daniel Furelos-Blanco, Charles Pert, Frederik Kelbel, Alex F. Spies, Alessandra Russo, Michael Dennis

AAAI 2026 · 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
use PLR-perp or ACCEL curricula instead of domain randomizationtask-level pair training · Minigrid task-level pairs, independent samplingCVaR / test solve rate: 2.7% solvable problems per batch; DR solves almost no problemsImproved
add level-conditioned problem sampling (83.4% solvable) for DR (ablation)DR · Hand-designed test setCVaR and test performance: 2.7% -> 83.4% solvable; DR matches ≈91.6%Improved
add level-conditioned problem sampling for PLR-perp and ACCEL (ablation)PLR-perp, ACCEL · Hand-designed test setCVaR and test performance: ≈1--3% gainsNo clear effect
use random walk-based DAG task sampler instead of sequential (ablation)PLR-perp · Hand-designed test setsolve rate: drop by ≈35% compared to the sequential settingHurt
add both level and task edits (vs disabling one type) (ablation)ACCEL · Minigrid task-level pairsperformanceImproved
use single-edit sequences instead of 7-10 edits (ablation)ACCEL · Minigrid task-level pairsperformance: ≈40% dropHurt
use 3-edit sequences instead of 7-10 edits (ablation)ACCEL · Minigrid task-level pairsperformance: ≈15% dropHurt
use 20-edit sequences instead of 7-10 edits (ablation)ACCEL · Minigrid task-level pairsperformance: ≈2% variationNo clear effect
add mutations (ACCEL) on top of curation (PLR-perp)PLR-perp · Hand-designed test setconvergence speedImproved

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