Cover Image

Mind the Model, Not the Agent: The Primacy Bias in Model-based RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qiao, Zhongjian, Lyu, Jiafei, Li, Xiu
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
by: Qiao, Zhongjian, et al.
Published: (2026)

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

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

SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning
by: Qiao, Zhongjian, et al.
Published: (2024)

World Models with Hints of Large Language Models for Goal Achieving
by: Liu, Zeyuan, et al.
Published: (2024)

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

Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning
by: Falzari, Massimiliano, et al.
Published: (2025)

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

The Primacy of Magnitude in Low-Rank Adaptation
by: Zhang, Zicheng, et al.
Published: (2025)

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

Debiased Model-based Representations for Sample-efficient Continuous Control
by: Lyu, Jiafei, et al.
Published: (2026)

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
by: Liu, Zeyuan, et al.
Published: (2025)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
by: Yang, Kai, et al.
Published: (2023)

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

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
by: Cheng, Jie, et al.
Published: (2024)

BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
by: Xie, Yuhan, et al.
Published: (2026)

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
by: Zhang, Qiang, et al.
Published: (2026)

Dual Alignment Maximin Optimization for Offline Model-based RL
by: Zhou, Chi, et al.
Published: (2025)

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
by: Zhan, Guojian, et al.
Published: (2025)

MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster
by: Feng, Laingjun, et al.
Published: (2025)

Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering
by: Qiao, Zhongjian, et al.
Published: (2025)

Are Expressive Models Truly Necessary for Offline RL?
by: Wang, Guan, et al.
Published: (2024)

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
by: Zhao, Kangwen, et al.
Published: (2025)

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
by: Lu, Rui, et al.
Published: (2025)

Modeling Others' Minds as Code
by: Jha, Kunal, et al.
Published: (2025)

Data-centric Federated Graph Learning with Large Language Models
by: Yan, Bo, et al.
Published: (2025)

OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment
by: Lim, Yooseok, et al.
Published: (2024)

Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
by: Plecko, Drago, et al.
Published: (2024)

CoMind: Towards Community-Driven Agents for Machine Learning Engineering
by: Li, Sijie, et al.
Published: (2025)

UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts
by: Wang, Fu-Yun, et al.
Published: (2025)

Meta-RL Induces Exploration in Language Agents
by: Jiang, Yulun, et al.
Published: (2025)

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
by: Chen, Jiaqi, et al.
Published: (2025)

ProgAgent:A Continual RL Agent with Progress-Aware Rewards
by: Tan, Jinzhou, et al.
Published: (2026)

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
by: Zhang, Yang, et al.
Published: (2024)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
by: Nie, Yuzhou, et al.
Published: (2024)

BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
by: Xie, Yuhan, et al.
Published: (2026)

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
by: Simmons-Edler, Riley, et al.
Published: (2025)

MindCraft: How Concept Trees Take Shape In Deep Models
by: Tian, Bowei, et al.
Published: (2025)

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling
by: Li, Ang, et al.
Published: (2026)