AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL

Zeyu Zhao, Yueling Che, Kaichen Liu, Jian Li, Junmei Yao

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 0 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
add Stage 3 sparse-region filling (K=1 instead of K=0) (ablation)MPFT-MOTD7 · Walker2d-2hypervolume (x10^7): 1.95 -> 2.04Improved
add Stage 3 sparse-region filling (K=1 instead of K=0) (ablation)MPFT-MOTD7 · Walker2d-2sparsity (x10^4, lower better): 2.09 -> 1.13Improved
increase K from 1 to 6 (ablation)MPFT-MOTD7 · Walker2d-2hypervolume (x10^7): 2.04 -> 2.15 -> 2.20Improved
increase K from 1 to 6 (ablation)MPFT-MOTD7 · Walker2d-2sparsity (x10^4, lower better): 1.13 -> 1.09 -> 0.89Improved
add Stage 3 sparse-region filling (K=1 instead of K=0) (ablation)MPFT-MOTD7 · HalfCheetah-2hypervolume (x10^6): 3.47 -> 3.51Improved
add Stage 3 sparse-region filling (K=1 instead of K=0) (ablation)MPFT-MOTD7 · HalfCheetah-2sparsity (x10^3, lower better): 5.95 -> 2.38Improved
increase K from 1 to 6 (ablation)MPFT-MOTD7 · HalfCheetah-2hypervolume (x10^6): 3.51 -> 3.52 -> 3.54Improved
increase K from 1 to 6 (ablation)MPFT-MOTD7 · HalfCheetah-2sparsity (x10^3, lower better): 2.38 -> 1.10 -> 0.63Improved
use MPFT framework instead of evolutionary frameworks (MOTD7 variant)MPFT-MOTD7 vs PGMORL/PA2D-MORL/C-MORL · <=3-objective MuJoCo envsenv_steps: decrease by 78.22%Improved
use MPFT framework instead of evolutionary frameworks (MOSAC variant)MPFT-MOSAC vs PGMORL/PA2D-MORL/C-MORL · <=3-objective MuJoCo envsenv_steps: decrease by 72.04%Improved
use MPFT framework instead of evolutionary frameworks (MOPPO variant)MPFT-MOPPO vs PGMORL/PA2D-MORL/C-MORL · <=3-objective MuJoCo envsenv_steps: decrease by 66.27%Improved
replace C-MORL with single-policy Pareto tracking (SPFT)SPFT · FT-6hypervolume (x10^4): 3.67 -> 5.02Improved

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