AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Michael Dennis, Natasha Jaques, Eugene Vinitsky, Alexandre Bayen, Stuart J. Russell, Andrew Critch, Sergey Levine

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 22 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 PAIRED (regret with antagonist) instead of minimax adversarynavigation agent · Labyrinth zero-shot transfersuccess rate (%): 10 -> 40Improved
Use PAIRED instead of minimax adversarynavigation agent · Maze zero-shot transfersuccess rate (%): 0.0 -> 18Improved
Use PAIRED instead of domain randomizationnavigation agent · Labyrinth zero-shot transfersuccess rate (%): 0.0 -> 40Improved
Use PAIRED instead of minimax or DR on easy transfer tasks (Empty, 50 Blocks)navigation agent · Empty and 50 Blocks transfersuccess rateNo clear effect
Use PAIRED instead of minimax adversary after adversary constraints are removedMuJoCo hopper agent · MuJoCo hopper with adversarial torquesrewardImproved
Compute regret with combined population or flexible approach that breaks the coordination assumption (ablation)PAIRED · Navigation emergent complexitysolved path lengthHurt

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