AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

MIRACLE: Model-free Imitation and Reinforcement Learning for Adaptive Cut-Selection

Arjun M., Rijul Tandon, Agam Gupta, HARIPRASAD KODAMANA, Manojkumar Ramteke

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing

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 weighted curriculum learning (ablation)MIRACLE · 45 test instancesavg speedup: 1.11× -> 1.34×Improved
add weighted curriculum learning (ablation)MIRACLE · 45 test instancessuccess rate: 94% -> 100%Improved
use PPO instead of TRPO (ablation)MIRACLE · 45 test instancesavg speedup: 1.355× -> 1.338×No clear effect
use PPO instead of SAC (ablation)MIRACLE · 45 test instancesavg speedup: 1.332× -> 1.338×No clear effect
use 3-layer MLP instead of 2-layer (ablation)MIRACLE · SetCoveravg speedup: 1.163× -> 1.161×No clear effect
increase expert data from 300 to 1000 instances (ablation)MIRACLE · SetCoveravg speedup: 1.092× -> 1.093×No clear effect
increase cut budget from 10 to 50 (ablation)MIRACLE inference · SetCoveravg speedup: 1.170 -> 1.157No clear effect
increase max iterations from 1 to 10 (ablation)MIRACLE inference · SetCoveravg speedup: 1.163 -> 1.166No clear effect
remove early stopping (ablation)MIRACLE inference · SetCoveravg speedup: 1.166 -> 1.164No clear effect
use MIRACLE cut selection instead of SCIP defaultSCIP 8.0 · SetCover and MIPLIB (300 instances)peak memory: 2,073.9 MB -> 284.7 MBImproved
use MIRACLE cut selection instead of SCIP baselineSCIP 8.0 · MIPLIB (Large)success rate: 53.3% -> 100.0%Improved
use MIRACLE instead of Wang et al. hierarchical modelcut selection · SetCover-Easypeak memory: ~500 MB -> ~46 MBImproved

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