AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

MTRL-CG: Multi-Task Reinforcement Learning Method with Spectral Clustering-Based Task Grouping

Wenjia Meng, Teng Zhang, Haoliang Sun, Yilong Yin

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous 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 MTRL-CG task groupingCARE · Meta-World MT10-Fixedmax success rate: 0.77 -> 0.97Improved
add MTRL-CG task groupingMT-SAC · Meta-World MT10-Mixedmax success rate: 0.70 -> 0.87Improved
add MTRL-CG task groupingCMTA · Meta-World MT10-Mixedfinal success rate: 0.58 -> 0.53Hurt
add MTRL-CG task groupingPaCo · Meta-World MT50-Fixedfinal success rate: 0.52 -> 0.51No clear effect
add MTRL-CG task groupingPaCo · Meta-World MT50-Mixedfinal success rate: 0.62 -> 0.66Improved
add MTRL-CG task groupingCMTA · Meta-World MT50-Fixedfinal success rate: 0.52 -> 0.59Improved
use spectral affinity grouping instead of HOA grouping (ablation)CARE · Meta-World MT10-Fixedmax success rate: 0.87 -> 0.97Improved
use spectral affinity grouping instead of random grouping (ablation)CARE · Meta-World MT10-Mixedfinal success rate: 0.47 -> 0.73Improved
use affinity-based grouping instead of no grouping (random grouping lowers it) (ablation)CARE · Meta-World MT10-Mixedfinal success rate: 0.69 -> 0.47Hurt
use 3 groups instead of 10 (ablation)CARE+MTRL-CG · Meta-World MT10-Mixedfinal success rate: 0.34 -> 0.73Improved
use 3 groups instead of 5 (ablation)CARE+MTRL-CG · Meta-World MT10-Mixedmax success rate: 0.72 -> 0.87Improved
use 3 groups instead of a single shared policy (1 group) (ablation)CARE+MTRL-CG · Meta-World MT10-Fixedmax success rate: 0.77 -> 0.97Improved

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