AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Test-time Offline Reinforcement Learning on Goal-related Experience

Marco Bagatella, Mert Albaba, Jonas Hübotter, Georg Martius, Andreas Krause

ICML 2026 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 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 goal-conditioned test-time training on selected dataGC-BC · pointmaze expertsuccess rate: 0.05 -> 0.78Improved
add GC-TTTGC-IQL-DDPG · antmaze playsuccess rate: 0.24 -> 0.68Improved
add GC-TTTSAW · cubesingle and antmazesuccess rate: 0.73 -> 0.71 (cubesingle)No clear effect
select random data instead of relevant and optimal data (ablation)GC-TTT with GC-IQL · pointmaze/antmaze playsuccess rate: 0.25 -> 0.22Hurt
add the optimality filter on top of relevance (ablation)GC-TTT with GC-IQL · pointmaze/antmaze playsuccess rate: 0.35 -> 0.57Improved
add the relevance filter on top of optimality (ablation)GC-TTT with GC-IQL · pointmaze/antmaze playsuccess rate: 0.34 -> 0.57Improved
increase TTT frequency (shorter horizon K) (ablation)GC-TTT with GC-IQL · antmaze playsuccess rateImproved
scale policy network width to match inference FLOPs instead of using TTT (ablation)GC-IQL policy · antmaze playsuccess rateNo clear effect
use critic-free variant (trajectory returns) instead of H-step value returns (ablation)GC-TTT · expert datasetssuccess rate: pointmaze expert GC-BC: 0.78 -> 0.76Mixed
increase the number of test-time gradient steps N (ablation)GC-TTT with GC-IQL · antmaze playsuccess rateMixed
replace reward-based relevance with a value-based relevance criterion (ablation)GC-TTT with GC-IQL · antmaze playsuccess rate: 0.73 -> 0.68No clear effect
inject modest Gaussian noise into value estimates (ablation)GC-TTT with GC-IQL · antmaze playsuccess rate: 0.73 -> 0.78 (alpha=0.1)No 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