Imagen de Portada

Debiased Model-based Representations for Sample-efficient Continuous Control

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lyu, Jiafei, Lin, Zichuan, Fujimoto, Scott, Yang, Kai, Chen, Yangkun, Yang, Saiyong, Lu, Zongqing, Ye, Deheng
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
por: Yang, Kai, et al.
Publicado: (2025)

Cross-Domain Policy Adaptation by Capturing Representation Mismatch
por: Lyu, Jiafei, et al.
Publicado: (2024)

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
por: Zhao, He, et al.
Publicado: (2026)

Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence
por: Lyu, Jiafei, et al.
Publicado: (2024)

Mildly Conservative Q-Learning for Offline Reinforcement Learning
por: Lyu, Jiafei, et al.
Publicado: (2022)

ProAct: Agentic Lookahead in Interactive Environments
por: Yu, Yangbin, et al.
Publicado: (2026)

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
por: Lin, Zichuan, et al.
Publicado: (2025)

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
por: Wei, Tong, et al.
Publicado: (2025)

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
por: Lin, Zichuan, et al.
Publicado: (2026)

Learning Versatile Skills with Curriculum Masking
por: Tang, Yao, et al.
Publicado: (2024)

PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning
por: Sun, Shengjie, et al.
Publicado: (2025)

A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation
por: Gong, Aicheng, et al.
Publicado: (2024)

CORD: Generalizable Cooperation via Role Diversity
por: Matsuyama, Kanefumi, et al.
Publicado: (2025)

CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
por: Chai, Qi, et al.
Publicado: (2025)

SEABO: A Simple Search-Based Method for Offline Imitation Learning
por: Lyu, Jiafei, et al.
Publicado: (2024)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
por: Qu, Yun, et al.
Publicado: (2026)

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
por: Wei, Tong, et al.
Publicado: (2025)

Mind the Model, Not the Agent: The Primacy Bias in Model-based RL
por: Qiao, Zhongjian, et al.
Publicado: (2023)

PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation
por: Lin, Zichuan, et al.
Publicado: (2025)

ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
por: Lyu, Jiafei, et al.
Publicado: (2024)

Temporal Difference Learning with Constrained Initial Representations
por: Lyu, Jiafei, et al.
Publicado: (2026)

The Lifecycle Principle: Stabilizing Dynamic Neural Networks with State Memory
por: Yang, Zichuan
Publicado: (2025)

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
por: Qu, Yun, et al.
Publicado: (2026)

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
por: Yang, Wenkai, et al.
Publicado: (2026)

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
por: Chen, Yangkun, et al.
Publicado: (2024)

HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
por: Chen, Ruyi, et al.
Publicado: (2026)

AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback
por: Zhang, Wanpeng, et al.
Publicado: (2023)

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
por: Zhou, Siyu, et al.
Publicado: (2024)

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
por: Zhou, Siyu, et al.
Publicado: (2025)

MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control
por: Zhu, Liwen, et al.
Publicado: (2024)

Revisiting Discrete Soft Actor-Critic
por: Zhou, Haibin, et al.
Publicado: (2022)

Debiasing Reward Models by Representation Learning with Guarantees
por: Ng, Ignavier, et al.
Publicado: (2025)

SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control
por: Wang, Yuxuan, et al.
Publicado: (2025)

Vul-R2: A Reasoning LLM for Automated Vulnerability Repair
por: Wen, Xin-Cheng, et al.
Publicado: (2025)

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
por: Shi, Bingkang, et al.
Publicado: (2023)

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
por: Lu, Zhicong, et al.
Publicado: (2026)

EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion
por: Yang, Zichuan, et al.
Publicado: (2025)

Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities
por: Zhu, Xiaoguang, et al.
Publicado: (2025)

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
por: Zhang, Xinyu, et al.
Publicado: (2024)

Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
por: Wen, Xin-Cheng, et al.
Publicado: (2025)