Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

TL;DR

Plan-Seq-Learn (PSL) leverages language models and motion planning to guide reinforcement learning, enabling robots to solve complex long-horizon tasks from raw visuals without pre-defined skills, achieving state-of-the-art results.

Contribution

The paper introduces PSL, a modular framework combining language-guided planning with RL to address long-horizon robotics tasks without pre-defined skill libraries.

Findings

Achieves over 85% success rate on 25+ challenging tasks.

Outperforms existing language-based and classical methods.

Effective on raw visual inputs across four benchmarks.

Abstract

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/