paper-with-me

홈 › Papers

Policy-shaped prediction: avoiding distractions in model-based reinforcement learning

2024-12-08 · Miles Hutson, Isaac Kauvar, Nick Haber

Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly predictable, but irrelevant to learning a good policy. Such scenarios can lead the model to exhaust its capacity on meaningless content, at the cost of neglecting important environment dynamics. While existing approaches attempt to solve this problem, we highlight its continuing impact on leading MBRL methods -- including DreamerV3 and DreamerPro -- with a novel environment where background distractions are intricate, predictable, and useless for planning future actions. To address this challenge we develop a method for focusing the capacity of the world model through synergy of a pretrained segmentation model, a task-aware reconstruction loss, and adversarial learning. Our method outperforms a variety of other approaches designed to reduce the impact of distractors, and is an advance towards robust model-based reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2412.05766

Code (0)

등록된 구현이 없습니다.

Tasks

Model-based Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Self-Consistent Model-based Adaptation for Visual Reinforcement Learning

2025-02-14 · Xinning Zhou, Chengyang Ying, Yao Feng, Hang Su 외

Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy's representations with hand-craft…

Denoisingreinforcement-learningReinforcement Learning

Sequential Action-Induced Invariant Representation for Reinforcement Learning

2023-09-22 · Dayang Liang, Qihang Chen, Yunlong Liu

How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a realistic and challenging problem in visual reinforcement learning. Recently, unsupervised repr…

Autonomous Drivingreinforcement-learningReinforcement LearningRepresentation Learning

When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning

2024-06-25 · Claas Voelcker, Tyler Kastner, Igor Gilitschenski, Amir-Massoud Farahmand

We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the representation learning problem in reinforcement learning. We also study how they interact with d…

Auxiliary LearningPredictionreinforcement-learningRepresentation Learning

Learning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing

2026-02-16 · Baixiao Huang, Baiyu Huang, Yu Hou arxiv

Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a major challenge for robot dogs to complete building constructio…

Reinforcement Learning

Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions

2022-05-20 · Rui Yang, Jie Wang, Zijie Geng, Mingxuan Ye 외

Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios. However, visual distractions -- which are common in real s…

Reinforcement Learning (RL)