Copertina

STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Goli, Hossein, Gimelfarb, Michael, de Lara, Nathan Samuel, Nishimura, Haruki, Itkina, Masha, Shkurti, Florian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation
di: Vincent, Joseph A., et al.
Pubblicazione: (2024)

SAFE: Multitask Failure Detection for Vision-Language-Action Models
di: Gu, Qiao, et al.
Pubblicazione: (2025)

Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping
di: Snyder, David, et al.
Pubblicazione: (2025)

Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison
di: Snyder, David, et al.
Pubblicazione: (2026)

What Do You Need for Compositional Generalization in Diffusion Planning?
di: Clark, Quentin, et al.
Pubblicazione: (2025)

Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
di: Xu, Chen, et al.
Pubblicazione: (2025)

CUPID: Curating Data your Robot Loves with Influence Functions
di: Agia, Christopher, et al.
Pubblicazione: (2025)

Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs
di: Gimelfarb, Michael, et al.
Pubblicazione: (2024)

Generative Trajectory Stitching through Diffusion Composition
di: Luo, Yunhao, et al.
Pubblicazione: (2025)

Impact of Different Failures on a Robot's Perceived Reliability
di: Violette, Andrew, et al.
Pubblicazione: (2026)

SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer
di: de Lara, Nathan Samuel, et al.
Pubblicazione: (2026)

Diversity You Can Actually Measure: A Fast, Model-Free Diversity Metric for Robotics Datasets
di: Sirigiri, Sreevardhan, et al.
Pubblicazione: (2026)

Improving Trajectory Stitching with Flow Models
di: O'Mahoney, Reece, et al.
Pubblicazione: (2025)

The Impact of Class Uncertainty Propagation in Perception-Based Motion Planning
di: Shah, Jibran Iqbal, et al.
Pubblicazione: (2026)

LOPR: Latent Occupancy PRediction using Generative Models
di: Lange, Bernard, et al.
Pubblicazione: (2022)

CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning
di: Kondo, Kota, et al.
Pubblicazione: (2024)

Continual Model-Based Reinforcement Learning with Hypernetworks
di: Huang, Yizhou, et al.
Pubblicazione: (2020)

Policy-Guided Diffusion
di: Jackson, Matthew Thomas, et al.
Pubblicazione: (2024)

SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions
di: Samavi, Sepehr, et al.
Pubblicazione: (2025)

Explore until Confident: Efficient Exploration for Embodied Question Answering
di: Ren, Allen Z., et al.
Pubblicazione: (2024)

IntOPE: Off-Policy Evaluation in the Presence of Interference
di: Bai, Yuqi, et al.
Pubblicazione: (2024)

Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving
di: Lange, Bernard, et al.
Pubblicazione: (2024)

Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation
di: Singh, Saurav, et al.
Pubblicazione: (2026)

Scalable Policy Evaluation with Video World Models
di: Tseng, Wei-Cheng, et al.
Pubblicazione: (2025)

Residual Off-Policy RL for Finetuning Behavior Cloning Policies
di: Ankile, Lars, et al.
Pubblicazione: (2025)

STITCH: Augmented Dexterity for Suture Throws Including Thread Coordination and Handoffs
di: Hari, Kush, et al.
Pubblicazione: (2024)

Off-dynamics Conditional Diffusion Planners
di: Ng, Wen Zheng Terence, et al.
Pubblicazione: (2024)

Contrast Sets for Evaluating Language-Guided Robot Policies
di: Anwar, Abrar, et al.
Pubblicazione: (2024)

Diffusion Policies for Generative Modeling of Spacecraft Trajectories
di: Briden, Julia, et al.
Pubblicazione: (2025)

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
di: Kim, Donghu, et al.
Pubblicazione: (2026)

Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
di: Huang, Kevin, et al.
Pubblicazione: (2025)

Does Unpredictability Influence Driving Behavior?
di: Samavi, Sepehr, et al.
Pubblicazione: (2023)

Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
di: Yang, Yu, et al.
Pubblicazione: (2026)

Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
di: Nakanishi, Kosuke, et al.
Pubblicazione: (2025)

Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration
di: Li, Guopeng, et al.
Pubblicazione: (2026)

STITCH 2.0: Extending Augmented Suturing with EKF Needle Estimation and Thread Management
di: Hari, Kush, et al.
Pubblicazione: (2025)

Diffusion Policy Policy Optimization
di: Ren, Allen Z., et al.
Pubblicazione: (2024)

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
di: Li, Ge, et al.
Pubblicazione: (2024)

Off Policy Lyapunov Stability in Reinforcement Learning
di: Gill, Sarvan, et al.
Pubblicazione: (2025)

$Δ\text{-}{\rm OPE}$: Off-Policy Estimation with Pairs of Policies
di: Jeunen, Olivier, et al.
Pubblicazione: (2024)