Plan-Seq-Learn: 言語モデルで誘導する強化学習による長期的ロボティクスタスクの解法
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
LLMの高レベル計画と運動計画を組み合わせ、事前定義されたスキルなしで強化学習を効率的に誘導し、最大10段階の長期的ロボティクスタスクを視覚入力から85%以上の成功率で解く手法を提案。
著者: Murtaza Dalal, Tarun Chiruvolu, Devendra Chaplot, Ruslan Salakhutdinov
分類: cs.LG, cs.AI, cs.CV, cs.RO
原文アブストラクト
Large Language Models (LLMs) have been shown to be capable of performing high-level planning for long-horizon robotics tasks, yet existing methods require access to a pre-defined skill library (e.g. picking, placing, pulling, pushing, navigating). However, LLM planning does not address how to design or learn those behaviors, which remains challenging particularly in long-horizon settings. Furthermore, for many tasks of interest, the robot needs to be able to adjust its behavior in a fine-grained manner, requiring the agent to be capable of modifying low-level control actions. Can we instead use the internet-scale knowledge from LLMs for high-level policies, guiding reinforcement learning (RL) policies to efficiently solve robotic control tasks online without requiring a pre-determined set of skills? In this paper, we propose Plan-Seq-Learn (PSL): a modular approach that uses motion planning to bridge the gap between abstract language and learned low-level control for solving long-horizon robotics tasks from scratch. We demonstrate that PSL achieves state-of-the-art results on over 25 challenging robotics tasks with up to 10 stages. PSL solves long-horizon tasks from raw visual input spanning four benchmarks at success rates of over 85%, out-performing language-based, classical, and end-to-end approaches. Video results and code at https://mihdalal.github.io/planseqlearn/
