AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower Interfaces

Yanning Dai, Yuhui Wang, Dylan R. Ashley, Jürgen Schmidhuber

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules

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 Stackelberg implicit differentiation to the leader gradient (vs BodyGen)BodyGen · Stepper-Regularfinal episode reward: 4685.94 -> 7215.20Improved
add Stackelberg gradient on challenging 3D tasksBodyGen · Crawler, Stepper-Regular, Stepper-Hard, Pusherfinal episode reward: +32.02%Improved
use Stackelberg PPO over strongest baseline across all environmentsBodyGen · all nine environmentsfinal episode reward: +20.66%Improved
add Stackelberg gradient on SwimmerBodyGen · Swimmerfinal episode reward: 1302.64 -> 1334.98No clear effect
add PPO clipping to SID (full vs SID-only) (ablation)SID estimator · Stepper-Regularfinal episode reward: 1257.33 -> 7215.20Improved
add SID to PPO (full vs PPO-only) (ablation)PPO · Stepper-Regularfinal episode reward: 4685.94 -> 7215.20Improved
use Fisher approximation instead of analytic Hessian (ablation)Stackelberg PPO · Stepper-Regularfinal episode reward: 2500 -> 6000Improved
use intermediate lambda (0.5 to 10) instead of lambda 0 or infinity (ablation)Stackelberg PPO · Stepper-Regularfinal episode rewardImproved
add PPO clipping at epsilon 0.2 instead of no clipping (ablation)Stackelberg PPO · Stepper-Regularfinal episode reward: 1233.26 -> 7215.20Improved
raise clipping threshold from 0.2 to 0.4 (ablation)Stackelberg PPO · Stepper-Regularfinal episode reward: 7215.20 -> 7907.01Improved
raise clipping threshold from 0.4 to 0.8 (ablation)Stackelberg PPO · Stepper-Regularfinal episode reward: 7907.01 -> 2656.92Hurt
raise leader horizon T from 3 to 5 (ablation)Stackelberg PPO · Stepper-Regularfinal episode reward: 6188.99 -> 7215.20Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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