Summary of Plan-seq-learn: Language Model Guided Rl For Solving Long Horizon Robotics Tasks, by Murtaza Dalal et al.
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
by Murtaza Dalal, Tarun Chiruvolu, Devendra Chaplot, Ruslan Salakhutdinov
First submitted to arxiv on: 2 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Plan-Seq-Learn (PSL) approach uses motion planning to bridge the gap between abstract language and learned low-level control for solving long-horizon robotics tasks from scratch. This modular method leverages internet-scale knowledge from Large Language Models (LLMs) to guide reinforcement learning (RL) policies in efficiently solving robotic control tasks online without requiring a pre-determined set of skills. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models can perform high-level planning for long-horizon robotics tasks, but existing methods require access to a pre-defined skill library. The proposed approach addresses this limitation by using the internet-scale knowledge from LLMs to guide RL policies in solving robotic control tasks online without requiring a pre-determined set of skills. |
Keywords
» Artificial intelligence » Reinforcement learning
