Cover Image

The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Sukai, Liu, Shu-Wei, Lipovetzky, Nir, Cohn, Trevor
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts
by: Huang, Sukai, et al.
Published: (2024)

Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
by: Huang, Sukai, et al.
Published: (2024)

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
by: Gumbsch, Christian, et al.
Published: (2026)

ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation
by: Feng, Youhe, et al.
Published: (2026)

Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models
by: Krack, Pierre, et al.
Published: (2026)

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
by: Zhang, Chen Bo Calvin, et al.
Published: (2024)

Diffusion Reward: Learning Rewards via Conditional Video Diffusion
by: Huang, Tao, et al.
Published: (2023)

Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions
by: Ishihara, Yu, et al.
Published: (2025)

Reward Machine Inference for Robotic Manipulation
by: Baert, Mattijs, et al.
Published: (2024)

Uncertainty-aware Reward Design Process
by: Yang, Yang, et al.
Published: (2025)

Curriculum Reinforcement Learning for Complex Reward Functions
by: Freitag, Kilian, et al.
Published: (2024)

On-Robot Reinforcement Learning with Goal-Contrastive Rewards
by: Biza, Ondrej, et al.
Published: (2024)

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
by: Liu, Yuyang, et al.
Published: (2025)

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution
by: Huang, Changxin, et al.
Published: (2024)

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning
by: Zeng, Runhao, et al.
Published: (2024)

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
by: Vasan, Gautham, et al.
Published: (2024)

Reward Redistribution via Gaussian Process Likelihood Estimation
by: Xiao, Minheng, et al.
Published: (2025)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
by: Xie, Tianbao, et al.
Published: (2023)

Robot Policy Learning with Temporal Optimal Transport Reward
by: Fu, Yuwei, et al.
Published: (2024)

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping
by: Miranda, Victor R. F., et al.
Published: (2022)

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL
by: Liu, Xin, et al.
Published: (2026)

Diffusion-Reward Adversarial Imitation Learning
by: Lai, Chun-Mao, et al.
Published: (2024)

Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward Scenarios
by: Clark, Emma, et al.
Published: (2024)

TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments
by: Hossain, Jumman, et al.
Published: (2024)

Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards
by: Guzey, Irmak, et al.
Published: (2024)

Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method
by: Yamani, Hoda, et al.
Published: (2025)

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
by: Tang, Nan, et al.
Published: (2025)

Momentum Based Reward Design for Low Emission Traffic Signal Control
by: Mundane, Chinmay, et al.
Published: (2026)

DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
by: Mu, Tongzhou, et al.
Published: (2024)

Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
by: Rathbun, Ethan, et al.
Published: (2026)

Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback
by: Zhang, Jenny, et al.
Published: (2024)

Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks
by: Choe, Jean Seong Bjorn, et al.
Published: (2024)

STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion
by: Wu, Zhenwei, et al.
Published: (2025)

Reward-Punishment Reinforcement Learning with Maximum Entropy
by: Wang, Jiexin, et al.
Published: (2024)

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
by: Chen, Letian, et al.
Published: (2024)

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
by: Venugopal, Aravind, et al.
Published: (2026)

Policy Learning from Large Vision-Language Model Feedback without Reward Modeling
by: Luu, Tung M., et al.
Published: (2025)

REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback
by: Chakraborty, Souradip, et al.
Published: (2023)

Decoupling Task and Behavior: A Two-Stage Reward Curriculum in Reinforcement Learning for Robotics
by: Freitag, Kilian, et al.
Published: (2026)

LORD: Large Models based Opposite Reward Design for Autonomous Driving
by: Ye, Xin, et al.
Published: (2024)