Learning Top-K Subtask Planning Tree Based on Discriminative Representation Pretraining for Decision-making  

作　　者：Jingqing Ruan Kaishen Wang Qingyang Zhang Dengpeng Xing Bo Xu 

机构地区：[1]Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China [2]School of Future Technology,University of Chinese Academy of Sciences,Beijing 100049,China [3]School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049,China

出　　处：《Machine Intelligence Research》2024年第4期782-800,共19页机器智能研究（英文版）

摘　　要：Decomposing complex real-world tasks into simpler subtasks and devising a subtask execution plan is critical for humans to achieve effective decision-making.However,replicating this process remains challenging for AI agents and naturally raises two questions:(1)How to extract discriminative knowledge representation from priors?(2)How to develop a rational plan to decompose complex problems?To address these issues,we introduce a groundbreaking framework that incorporates two main contributions.First,our multiple-encoder and individual-predictor regime goes beyond traditional architectures to extract nuanced task-specific dynamics from datasets,enriching the feature space for subtasks.Second,we innovate in planning by introducing a top-K subtask planning tree generated through an attention mechanism,which allows for dynamic adaptability and forward-looking decision-making.Our framework is empirically validated against challenging benchmarks BabyAI including multiple combinatorially rich synthetic tasks(e.g.,GoToSeq,SynthSeq,BossLevel),where it not only outperforms competitive baselines but also demonstrates superior adaptability and effectiveness incomplex task decomposition.

关 键 词：Reinforcement learning representation learning subtask planning task decomposition pretraining. 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]