AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning to Reconfigure: Configuration-Control Co-optimization of Reconfigurable Robots for Heterogeneous Locomotion

Xiaoyu Xiong, Kehan Liu, Huiyi Yan, Shengjie Wang, Yang Gao, Tao Du

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer

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 epsilon-greedy exploration to the design tails (ablation)Learning to Reconfigure · Fly-Walk (Mount)normalized traversal progress S: 0.335 -> 1.978Improved
add epsilon-greedy exploration to the design tails (ablation)Learning to Reconfigure · Wheel-Fly (Mount)normalized traversal progress S: 3.820 -> 7.368Improved
add epsilon-greedy exploration to the design tails (ablation)Learning to Reconfigure · Wheel-Legnormalized traversal progress S: 8.923 -> 9.148Improved
add staged optimization (freeze lock angle tail initially) (ablation)Learning to Reconfigure · Wheel-Fly (Mount)normalized traversal progress S: 0.325 -> 7.368Improved
add staged optimization (freeze lock angle tail initially) (ablation)Learning to Reconfigure · Fly-Walk (Mount)normalized traversal progress S: 0.437 -> 1.978Improved
use hierarchical primitives plus scheduler instead of end-to-end single policy (ablation)Learning to Reconfigure · 7 heterogeneous locomotion tasksnormalized traversal progress S: 9.83x average boostImproved
use learned scheduler instead of rule-based heuristic scheduler (ablation)Learning to Reconfigure · 7 heterogeneous locomotion tasksnormalized traversal progress SImproved
use reconfigurable learned configurations instead of non-reconfigurable co-design (BodyGen, GLSO)Learning to Reconfigure · 7 heterogeneous locomotion tasksnormalized traversal progress S: 10.52x BodyGen; 9.10x GLSO on averageImproved
use learned configurations instead of human domain-expert configurationsLearning to Reconfigure · 7 heterogeneous locomotion tasksnormalized traversal progress S: 1.19x on averageImproved
use PPO without reconfigurationPPO · Car-Leg (Narrow)normalized traversal progress S: 2.318 vs 2.618 (ours)Mixed
train BodyGen/GLSO from the same initial morphology instead of scratchBodyGen, GLSO · Fly-Walk (Mount) and Car-Legnormalized traversal progress S: BodyGen 0.498 -> 0.452; GLSO 0.507 -> 0.496No clear effect

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