paper-with-me

Papers

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

2022-10-13 · Shaohui Peng, Xing Hu, Rui Zhang, Ke Tang, Jiaming Guo, Qi Yi, Ruizhi Chen, Xishan Zhang, Zidong Du, Ling Li, Qi Guo, Yunji Chen

Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically discover high-quality hierarchical structures is still a great challenge. Previous HRL methods can hardly discover the hierarchical structures in complex environments due to the low exploration efficiency by exploiting the randomness-driven exploration paradigm. To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments. The key insight is that the causalities among environment variables are naturally fit for modeling reachable subgoals and their dependencies and can perfectly guide to build high-quality hierarchical structures. The results in two complex environments, 2D-Minecraft and Eden, show that CDHRL significantly boosts exploration efficiency with the causality-driven paradigm.

📄 PDF Abstract BibTeX arXiv:2210.06964

Code (0)

등록된 구현이 없습니다.

Tasks

Hierarchical Reinforcement LearningMinecraftreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

From Query Tools to Causal Architects: Harnessing Large Language Models for Advanced Causal Discovery from Data

2023-06-29 · Taiyu Ban, Lyvzhou Chen, Xiangyu Wang, Huanhuan Chen

Large Language Models (LLMs) exhibit exceptional abilities for causal analysis between concepts in numerous societally impactful domains, including medicine, science, and law. Recent research on LLM performance in variou…

Causal Discovery

Scalable and Hybrid Ensemble-Based Causality Discovery

2020-12-24 · Pei Guo, Achuna Ofonedu, Jianwu Wang

Causality discovery mines cause-effect relationships among different variables of a system and has been widely used in many disciplines including climatology and neuroscience. To discover causal relationships, many data-…

BenchmarkingDistributed ComputingTime SeriesTime Series Analysis

Order-based Causal Discovery for Multistage Processes

2026-07-04 · Eun-Yeol Ma, Junsub Jung, Heeyoung Kim arxiv

Causality has become an increasingly important tool for gaining a deeper understanding of complex systems. Among various causal analysis methods, causal discovery, which identifies causal relationships among variables fr…

Computational Efficiency

Enhancing the Performance of Neural Networks Through Causal Discovery and Integration of Domain Knowledge

2023-11-29 · Xiaoge Zhang, Xiao-Lin Wang, Fenglei Fan, Yiu-ming Cheung 외

In this paper, we develop a generic methodology to encode hierarchical causality structure among observed variables into a neural network in order to improve its predictive performance. The proposed methodology, called c…

Causal Discovery

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

2021-07-02 · Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal 외

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as r…

BenchmarkingCausal DiscoveryModel-based Reinforcement Learningreinforcement-learning+2