AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization

Saeed Hedayatian, Stefanos Nikolaidis

ICLR 2026 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL · 3 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 learned random-feature policy embeddings with weighted PCA descriptors instead of hand-crafted descriptorsCMA-MAE QD · AntGT QD Score (x10^4): 182.58 -> 361.43Improved
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · BipedalWalkerGT QD Score (x10^4): 1.81 -> 6.09Improved
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · SwimmerVendi Score: 4.67 -> 16.92Improved
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · Walker2dqVS: 9.08 -> 7.22Hurt
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · Walker2dVendi Score: 10.17 -> 8.4Hurt
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · HalfCheetahqVS: 2.07 -> 1.35Hurt
use AutoQD instead of Aurora learned descriptorsCMA-MAE QD · HalfCheetahVendi Score: 5.8 -> 5.29Hurt
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · HalfCheetahGT QD Score (x10^4): 24.91 -> 30.78Improved
use AutoQD instead of hand-crafted descriptorsCMA-MAE QD · HopperqVS: 1.35 -> 1.94Improved
use AutoQD population under altered frictionbest policy · BipedalWalker (varying friction)AUC: 1309.41 -> 1429.66Improved
use AutoQD population under altered massbest policy · BipedalWalker (varying mass scale)AUC: 271.83 -> 295.65Improved
use AutoQD instead of RegularQD under altered frictionbest policy · BipedalWalker (varying friction)AUC: 30.27 -> 1429.66Improved

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