AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Marco Jiralerspong, Esther Derman, Danilo Vucetic, Nikolay Malkin, Bilun Sun, Tianyu Zhang, Pierre-Luc Bacon, Gauthier Gidel

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 2 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 trajectory general mellowmax (q=0.75) instead of GFNGFN · GFPaverage mode reward: 1.90 -> 2.95Improved
use TGM q=0.75 instead of GFNGFN · AMPaverage mode reward: 10.04 -> 10.43Improved
use TGM q=0.75 instead of GFNGFN · UTRaverage mode reward: 4.12 -> 4.27Improved
raise q from 0.25 to 1.0 in TGMTGM · GFPaverage mode reward: 2.95 -> 2.05Hurt
use q=1.0 instead of q=0.75 in TGMTGM · AMPaverage mode reward: 10.43 -> 10.29No clear effect
use TGM instead of PPOPPO · GFPaverage mode reward: 0.66 -> 2.95Improved
use TGM instead of SACSAC · AMPaverage mode reward: 5.69 -> 10.43Improved
use TGM/TB instead of PPOPPO · GFPtraining speed (samples/s): 8 -> 120Improved
use TGM instead of PPOPPO · AMPaverage mode reward: 9.79 -> 10.13No 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