Reward-Prediction Error

Follow this topic Ask about this topic

Recent momentum

+67%

5 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Reward-Prediction Error.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Reward-Prediction Error.

Period ending 2026-09-07

4 new papers

A weekly snapshot of new work published in Reward-Prediction Error.

33 papers

Latest in Reward-Prediction Error

Browse all topics →

Protocol before progress: leakage-aware evaluation of AIS trajectory prediction
Sep 22, 2026Zobeir Raisi, Vali Mohammad Nazarzehi HadTrajectory Prediction Automatic Identification System
Learned Look-Ahead Splitting Rule for CART
Sep 14, 2026Andrew Gao, Tianlin Liu, Ruichen Han +1Decision Trees Lookahead
Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing Degradation
Sep 7, 2026Geonmyeong Lee, Byoung-Tak ZhangWorld Models Reward-Prediction Error
Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs
Sep 1, 2026Runze Xu, Xiaolong Shan, Shuang Dai +2Vision-Language-Action Models Cross-Attention
When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation
Aug 30, 2026Cong CaoCausal Inferences Reward-Prediction Error
The Intervention Gap in Latent World Models
Aug 30, 2026Donna VakalisReward-Prediction Error
Hierarchical Solomonoff Induction: An Unbounded Machine Learning Model
Aug 2, 2026Nathan YoungSequence Modeling Machine Learning
A reproducible and extensible framework for benchmarking competing risks survival models
Jul 31, 2026Begoña B. Sierra, Colin McLean, Peter S. Hall +2Survival Analysis Reward-Prediction Error
Explicit Note-Event Tokenization and Pitch-Validity Constrained Decoding for MIDI-to-Tablature Transcription
Jul 29, 2026Ting-Kai Hsu, Wei-Chin Wang, Kai-Xi Hong +1Sheet Music Transcription
Optimal Recalibration of an Online Predictor
Jul 22, 2026Lunjia Hu, Kevin Tian, Chutong YangRecalibration Multicalibration and Calibration
A Control Theory of Predictability in Latent World Models
Jul 11, 2026Hanzhe You, Yonggang Zhang, Maohao Ran +6Latent World Models Reward-Prediction Error
Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models
Jul 5, 2026Donna VakalisReward-Prediction Error Latent World Models
What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning
Jun 30, 2026Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky +1Autonomous Driving Trajectory Prediction
An Integrated Machine Learning and Hierarchical Variance Decomposition Pipeline for Student Performance Prediction and Metacognitive Calibration on Multi-Signal Telemetry
Jun 27, 2026Gurdeep Singh VirdeeReward-Prediction Error Logistic Regression
Understanding Rollout Error in Graph World Models
Jun 26, 2026Xinyuan Song, Zekun CaiLong Rollouts World Models
Beyond Accuracy: Measuring Logical Compliance of Predictive Models
Jun 18, 2026Guillaume Olivier Delplanque, Pierre Genevès, Nabil Layaïda +1Clinical Prediction Reward-Prediction Error
When Does q-error Predict Plan Regret? Three Regimes of Cardinality-Estimation Error
Jun 14, 2026Madhulatha Mandarapu, Sandeep KunkunuruReward-Prediction Error Estimators
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
Jun 11, 2026Hongbo WangWorld Models Reward-Prediction Error
SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration
Jun 9, 2026Barsat Khadka, Kawsher Roxy, Md Rubel AhmedClocks Physics-Guided Deep Learning Framework
Prediction Under Imperfect Compression: A Theory of Approximate MDL
Jun 3, 2026Qian Li, Xinyu Mao, Shang-Hua Teng +1Maximum Likelihood Reward-Prediction Error
When Offline Selectors Cannot Beat the Best Single Model: A Diagnostic Study on edX Dropout Prediction
Jun 2, 2026Tyler Crosse, Alan Nadelsticher Ruvalcaba, Dustin Khang LeDuc +3Model Selection Reward-Prediction Error
The Role of Ambiguity in Error Prediction via Uncertainty Quantification
Jun 1, 2026Ieva Raminta Staliūnaitė, James Bishop, Andreas VlachosLarge Language Model Uncertainty Reward-Prediction Error
CRB-Guided Framework Design and Resource Allocation for Indoor mmWave ISCC Systems
May 28, 2026Zhonghao Liu, Yahao Ding, Yinchao Yang +1Integrated Sensing And Communication Millimeter Wave
Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference
May 16, 2026Mengtian Yang, Zhekun Zhang, Mingheng Wu +3Large Models Large Language Model Performance
MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware
May 7, 2026Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathore +3Egocentric Dataset Scalable Robot Data Synthesis
The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence
May 6, 2026Kejun LiuCausal Representation Learning Reward-Prediction Error
Decision-Focused Learning via Tangent-Space Projection of Prediction Error
May 2, 2026Junhyeong Lee, Sangjin Jin, Yongjae LeeLinear Regret Reward-Prediction Error
Recipes for Calibration Checks in Safety-Critical Applications
Apr 29, 2026Romeo ValentinMulticalibration and Calibration Reward-Prediction Error
MetaErr: Towards Predicting Error Patterns in Deep Neural Networks
Apr 25, 2026Varun Totakura, Shayok ChakrabortyDeep Learning Reward-Prediction Error
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Apr 20, 2026Vin Bhaskara, Haicheng WangReward-Prediction Error External Reward Models
Fewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Series Forecasting
Mar 10, 2025Jianqi Zhang, Yuchan Liu, Zeen Song +2Transformer Architectures Reward-Prediction Error
Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints
Date pendingQinzhen Ma (Rice University)Tactile World Model Ground Reaction Forces
A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models
Date pendingNanxing Nick Deng, Qing Cheng, Niclas Zeller +1Feed-Forward 3D Reconstruction Reconstruction Error

Sep 22, 2026 · cs.LGJ/K move · Enter open · S save

Protocol before progress: leakage-aware evaluation of AIS trajectory prediction

Zobeir Raisi, Vali Mohammad Nazarzehi Had

Reported gains in vessel-trajectory prediction from Automatic Identification System (AIS) data are credited to new architectures, but the evaluation protocol is rarely measured as a source of error reduction. We build a leakage-aware protocol with vessel-, time- and region-disjoint splits and apply it to two corpora with different traffic: 31 days of Danish national AIS traffic and 30 days of US Gulf coast traffic off Houston and Galveston. On both, we audit TrAISformer, GATransformer, and controlled AISFormer-inspired reconstructions. Three protocol effects appear in both corpora. First, TrAISformer's best-of-16 oracle decoder lowers error by a factor of 2.1-3.2 relative to greedy decoding. Second, a split that shares vessels lowers its greedy error by 23-25% at one hour, against 2% or less for a compact 0.43 M-parameter encoder. Third, a region-disjoint split raises TrAISformer's one-hour error from 2.2 to 24.6 km on the US corpus, because 99.9% of the test contexts fall in longitude bins never seen in training; the encoder built on local offsets is unaffected by this. Architectural mechanisms matter less: GATransformer's graph attention gives no measurable benefit on either corpus, while its waterway feature is worth 12-22%. The effect of a time-disjoint split is not stable across corpora (13% versus 2%). We release the splits and code.

Trajectory Prediction Automatic Identification System Reward-Prediction Error

Open paper Ask about it PDF