Image de couverture de livre

Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Xuyang, Yan, Keyu, Cao, Wenhan, Zhao, Lin
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning
par: Chen, Xuyang, et autres
Publié: (2025)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
par: Mao, Yixiu, et autres
Publié: (2024)

One-Step Sampler for Boltzmann Distributions via Drifting
par: Cao, Wenhan, et autres
Publié: (2026)

Variational OOD State Correction for Offline Reinforcement Learning
par: Jiang, Ke, et autres
Publié: (2025)

Active Advantage-Aligned Online Reinforcement Learning with Offline Data
par: Liu, Xuefeng, et autres
Publié: (2025)

An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space
par: Lin, Hai, et autres
Publié: (2024)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
par: Zhang, Tianle, et autres
Publié: (2024)

SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning
par: Li, Xuyang, et autres
Publié: (2025)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
par: Liu, Tenglong, et autres
Publié: (2024)

Flow Matching for Offline Reinforcement Learning with Discrete Actions
par: Khan, Fairoz Nower, et autres
Publié: (2026)

An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces
par: Beeson, Alex, et autres
Publié: (2024)

FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
par: Koirala, Prajwal, et autres
Publié: (2024)

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
par: Alles, Marvin, et autres
Publié: (2024)

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
par: Xu, Yinglun, et autres
Publié: (2023)

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
par: Cao, Wenhan, et autres
Publié: (2024)

Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator
par: Chen, Xuyang, et autres
Publié: (2025)

A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
par: Qing, Yunpeng, et autres
Publié: (2024)

Offline Reinforcement Learning with Penalized Action Noise Injection
par: Oh, JunHyeok, et autres
Publié: (2025)

M3OOD: Automatic Selection of Multimodal OOD Detectors
par: Qin, Yuehan, et autres
Publié: (2025)

Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
par: Wiltzer, Harley, et autres
Publié: (2024)

Offline Trajectory Optimization for Offline Reinforcement Learning
par: Zhao, Ziqi, et autres
Publié: (2024)

BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
par: Landers, Matthew, et autres
Publié: (2024)

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
par: Huang, Dongchi, et autres
Publié: (2025)

Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
par: Yao, Qingmao, et autres
Publié: (2025)

Mutual Information Regularized Offline Reinforcement Learning
par: Ma, Xiao, et autres
Publié: (2022)

SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance
par: Zhang, Liyu, et autres
Publié: (2024)

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
par: Ren, Qingnan, et autres
Publié: (2026)

Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning
par: Dong, Jinzong, et autres
Publié: (2026)

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation
par: Cao, Hongye, et autres
Publié: (2025)

An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning
par: Liu, Xingtu
Publié: (2025)

Information-Directed Offline-to-Online Reinforcement Learning
par: Chen, Keru
Publié: (2026)

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
par: Kim, Jeonghye, et autres
Publié: (2025)

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
par: Pan, Minting, et autres
Publié: (2025)

Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations
par: Ayabe, Shingo, et autres
Publié: (2024)

DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions
par: Li, Zongyue, et autres
Publié: (2025)

OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
par: Yao, Yihang, et autres
Publié: (2024)

Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach
par: Wang, Yue, et autres
Publié: (2023)

MetaOOD: Automatic Selection of OOD Detection Models
par: Qin, Yuehan, et autres
Publié: (2024)

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
par: Koirala, Prajwal, et autres
Publié: (2024)

A Non-Monolithic Policy Approach of Offline-to-Online Reinforcement Learning
par: Kim, JaeYoon, et autres
Publié: (2024)