paper-with-me

Papers

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

2021-07-15 · Kevin Li, Abhishek Gupta, Ashwin Reddy, Vitchyr Pong, Aurick Zhou, Justin Yu, Sergey Levine

Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Can we define a more tractable class of RL problems, where the agent is provided with examples of successful outcomes? In this problem setting, the reward function can be obtained automatically by training a classifier to categorize states as successful or not. If trained properly, such a classifier can provide a well-shaped objective landscape that both promotes progress toward good states and provides a calibrated exploration bonus. In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes. We propose a novel mechanism for obtaining these calibrated, uncertainty-aware classifiers based on an amortized technique for computing the normalized maximum likelihood (NML) distribution. To make this tractable, we propose a novel method for computing the NML distribution by using meta-learning. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions, while also providing more effective guidance towards the goal. We demonstrate that our algorithm solves a number of challenging navigation and robotic manipulation tasks which prove difficult or impossible for prior methods.

📄 PDF Abstract BibTeX arXiv:2107.07184

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning

2026-09-04 · Ahmad Mousavi, Majid Alikhani, Yeon-Chang Lee, Roberto Corizzo 외 arxiv

Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current architectures face two bottlenecks: structural rigidity, from a reliance o…

Multimodal Recommendation

CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask Guidance

2025-08-10 · Yingtie Lei, Fanghai Yi, Yihang Dong, Weihuang Liu 외 arxiv

Murals, as invaluable cultural artifacts, face continuous deterioration from environmental factors and human activities. Digital restoration of murals faces unique challenges due to their complex degradation patterns and…

High-Fidelity Mural Restoration via a Unified Hybrid Mask-Aware Transformer

2026-04-05 · Jincheng Jiang, Qianhao Han, Chi Zhang, Zheng Zheng arxiv

Ancient murals are valuable cultural artifacts, but many have suffered severe degradation due to environmental exposure, material aging, and human activity. Restoring these artworks is challenging because it requires bot…

Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning

2026-02-26 · Qiannian Zhao, Chen Yang, Jinhao Jing, Yunke Zhang 외 arxiv

Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet m…

Reinforcement LearningQuestion Answering

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

2023-01-27 · Daesol Cho, Seungjae Lee, H. Jin Kim

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex …

reinforcement-learningReinforcement Learning (RL)