AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RL

Alfredo Reichlin, Adriano Pacciarelli, Danica Kragic, Miguel Vasco

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 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
use MetricMM fusion instead of ConCat under Failure corruption p=0.5SAC on Fetch Slide · Fetch Slide, Failure two modalities (p=0.5)return: 4.01 -> 5.95Improved
use MetricMM instead of AMDF at low Patch corruption p=0.1SAC on Fetch PickAndPlace · Fetch PickAndPlace Patch (p=0.1)return: 2.2 -> 1.91Hurt
use MetricMM instead of best baseline at Patch p=0.5SAC on Fetch PickAndPlace · Fetch PickAndPlace Patch (p=0.5)return: -1.04 -> 1.43Improved
use MetricMM instead of baselines when only point cloud is corruptedSAC on Fetch Slide · Fetch Slide Failure, point cloud onlyreturn: 9.27 -> 7.87No clear effect
use MetricMM when single modality image-only corrupted (vs ConCat)SAC on Fetch Slide · Fetch Slide Failure, image onlyreturn: 0.28 -> 7.29Improved
inject noise during training of baselines (ablation)CURL/GMC/ConCat/LinearComb on Hopper-v5 · Hopper-v5training returnHurt
add multimodal invariance loss (ablation)MetricMM · pendulum with Gaussian noisereturn under noiseImproved
add metric loss pair L+ and L- (ablation)MetricMM · pendulum with Gaussian noisereturn under noiseImproved

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