日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

強化学習/長期的タスクarXiv:2312.15578

明示的・暗黙的サブゴール計画によるスパース報酬下の長期的タスク

Explicit-Implicit Subgoal Planning for Long-Horizon Tasks with Sparse Reward

シェア:XThreadsFacebookLINEはてブBluesky

人間の思考を模した明示的・暗黙的モデルでサブゴールを生成し、事後サンプリングと価値選択で品質を高める強化学習アルゴリズムを提案。シミュレーションと実世界の長期的タスクで有効性を示した。

著者: Fangyuan Wang, Anqing Duan, Peng Zhou, Shengzeng Huo, Guodong Guo, Chenguang Yang, David Navarro-Alarcon

分類: cs.RO

原文アブストラクト

The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel algorithm, termed Explicit-Implicit Subgoal Planning (EISP), designed to tackle long-horizon tasks through a divide-and-conquer approach. We utilize two primary criteria, feasibility and optimality, to ensure the quality of the generated subgoals. EISP consists of three components: a hybrid subgoal generator, a hindsight sampler, and a value selector. The hybrid subgoal generator uses an explicit model to infer subgoals and an implicit model to predict the final goal, inspired by way of human thinking that infers subgoals by using the current state and final goal as well as reason about the final goal conditioned on the current state and given subgoals. Additionally, the hindsight sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. While the value selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct four long-horizon tasks in both simulation and the real world. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods. These experimental results can be seen on the website \url{https://sites.google.com/view/vaesi}.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI