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arXiv:2311.15960

プログラムマシンポリシー:プログラム合成と状態機械を統合した長期的タスクへの取り組み

Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines

シェア:XThreadsFacebookLINEはてブBluesky

プログラム合成と状態機械を組み合わせ、多様なプログラムを状態機械のモードとして学習することで、長期的タスクを解き、未学習のより長いタスクにも汎化できる強化学習手法を提案。

著者: Yu-An Lin, Chen-Tao Lee, Guan-Ting Liu, Pu-Jen Cheng, Shao-Hua Sun

分類: cs.LG, cs.AI, cs.PL, cs.RO

原文アブストラクト

Deep reinforcement learning (deep RL) excels in various domains but lacks generalizability and interpretability. On the other hand, programmatic RL methods (Trivedi et al., 2021; Liu et al., 2023) reformulate RL tasks as synthesizing interpretable programs that can be executed in the environments. Despite encouraging results, these methods are limited to short-horizon tasks. On the other hand, representing RL policies using state machines (Inala et al., 2020) can inductively generalize to long-horizon tasks; however, it struggles to scale up to acquire diverse and complex behaviors. This work proposes the Program Machine Policy (POMP), which bridges the advantages of programmatic RL and state machine policies, allowing for the representation of complex behaviors and the address of long-term tasks. Specifically, we introduce a method that can retrieve a set of effective, diverse, and compatible programs. Then, we use these programs as modes of a state machine and learn a transition function to transition among mode programs, allowing for capturing repetitive behaviors. Our proposed framework outperforms programmatic RL and deep RL baselines on various tasks and demonstrates the ability to inductively generalize to even longer horizons without any fine-tuning. Ablation studies justify the effectiveness of our proposed search algorithm for retrieving a set of programs as modes.

関連論文

  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. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXO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
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI