paper-with-me

Papers

Landmark Guided Active Exploration with State-specific Balance Coefficient

2023-06-30 · Fei Cui, Jiaojiao Fang, Mengke Yang, Guizhong Liu

Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results across a variety of domains. However, the high-level policy's action space is often excessively large, presenting a significant challenge to effective exploration and resulting in potentially inefficient training. In this paper, we design a measure of prospect for sub-goals by planning in the goal space based on the goal-conditioned value function. Building upon the measure of prospect, we propose a landmark-guided exploration strategy by integrating the measures of prospect and novelty which aims to guide the agent to explore efficiently and improve sample efficiency. In order to dynamically consider the impact of prospect and novelty on exploration, we introduce a state-specific balance coefficient to balance the significance of prospect and novelty. The experimental results demonstrate that our proposed exploration strategy significantly outperforms the baseline methods across multiple tasks.

📄 PDF Abstract BibTeX arXiv:2306.17484

Code (0)

등록된 구현이 없습니다.

Tasks

Hierarchical Reinforcement Learning

Similar Papers 제목 키워드 기반

Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

2021-10-26 · NeurIPS 2021 12 · Junsu Kim, Younggyo Seo, Jinwoo Shin

Goal-conditioned hierarchical reinforcement learning (HRL) has shown promising results for solving complex and long-horizon RL tasks. However, the action space of high-level policy in the goal-conditioned HRL is often la…

Efficient ExplorationHierarchical Reinforcement Learningreinforcement-learningReinforcement Learning+1

Learning Continuous Control Policies for Information-Theoretic Active Perception

2022-09-26 · Pengzhi Yang, YuHan Liu, Shumon Koga, Arash Asgharivaskasi 외

This paper proposes a method for learning continuous control policies for active landmark localization and exploration using an information-theoretic cost. We consider a mobile robot detecting landmarks within a limited …

continuous-controlContinuous Control

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

2019-06-17 · Zhusi Zhong, Jie Li, Zhenxi Zhang, Zhicheng Jiao 외

Cephalometric tracing method is usually used in orthodontic diagnosis and treatment planning. In this paper, we propose a deep learning based framework to automatically detect anatomical landmarks in cephalometric X-ray …

Decoderregression

A Neuromorphic Vision-Based Measurement for Robust Relative Localization in Future Space Exploration Missions

2022-06-23 · Mohammed Salah, Mohammed Chehadah, Muhammed Humais, Mohammed Wahbah 외

Space exploration has witnessed revolutionary changes upon landing of the Perseverance Rover on the Martian surface and demonstrating the first flight beyond Earth by the Mars helicopter, Ingenuity. During their mission …

IngenuityLandmark Tracking

Facial Expression Translation using Landmark Guided GANs

2022-09-05 · Hao Tang, Nicu Sebe

We propose a simple yet powerful Landmark guided Generative Adversarial Network (LandmarkGAN) for the facial expression-to-expression translation using a single image, which is an important and challenging task in comput…

Facial Expression TranslationGenerative Adversarial NetworkTranslation