Large Language Models as Generalizable Policies for Embodied Tasks
- URL: http://arxiv.org/abs/2310.17722v2
- Date: Tue, 16 Apr 2024 17:54:06 GMT
- Title: Large Language Models as Generalizable Policies for Embodied Tasks
- Authors: Andrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure, Walter Talbott, Katherine Metcalf, Natalie Mackraz, Devon Hjelm, Alexander Toshev,
- Abstract summary: We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks.
Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment.
- Score: 50.870491905776305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and act solely through environmental interactions. We show that LLaRP is robust to complex paraphrasings of task instructions and can generalize to new tasks that require novel optimal behavior. In particular, on 1,000 unseen tasks it achieves 42% success rate, 1.7x the success rate of other common learned baselines or zero-shot applications of LLMs. Finally, to aid the community in studying language conditioned, massively multi-task, embodied AI problems we release a novel benchmark, Language Rearrangement, consisting of 150,000 training and 1,000 testing tasks for language-conditioned rearrangement. Video examples of LLaRP in unseen Language Rearrangement instructions are at https://llm-rl.github.io.
Related papers
- Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language.
Currently, instruction-tuned large language models (LLMs) excel at various English tasks.
Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
arXiv Detail & Related papers (2024-10-26T00:39:44Z) - Bridging Environments and Language with Rendering Functions and Vision-Language Models [7.704773649029078]
Vision-language models (VLMs) have tremendous potential for grounding language.
This paper introduces a novel decomposition of the problem of building language-conditioned agents (LCAs)
We also explore several enhancements to the speed and quality of VLM-based LCAs.
arXiv Detail & Related papers (2024-09-24T12:24:07Z) - Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs [7.746160514029531]
We demonstrate experimental results with LLMs that address robotics task planning problems.
Our approach acquires text descriptions of the task and scene objects, then formulates task planning through natural language reasoning.
Our approach is evaluated on a multi-modal prompt simulation benchmark.
arXiv Detail & Related papers (2024-03-20T17:58:12Z) - Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in
Low-Resource Languages [0.0]
"prompting" is where a user provides a description of a task and some completed examples of the task to a PLM as context before prompting the PLM to perform the task on a new example.
We consider three methods: few-shot prompting (prompt), language-adaptive fine-tuning (LAFT), and neural machine translation (translate)
We find that translate and prompt settings are a compute-efficient and cost-effective method of few-shot prompting for the selected low-resource languages.
arXiv Detail & Related papers (2024-03-09T21:36:13Z) - LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language
Models [56.25156596019168]
This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs)
Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
arXiv Detail & Related papers (2023-11-30T03:59:31Z) - UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions [64.50935101415776]
We build a single model that jointly performs various spoken language understanding (SLU) tasks.
We demonstrate the efficacy of our single multi-task learning model "UniverSLU" for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages.
arXiv Detail & Related papers (2023-10-04T17:10:23Z) - Pre-Training to Learn in Context [138.0745138788142]
The ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context.
We propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models' in-context learning ability.
Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters.
arXiv Detail & Related papers (2023-05-16T03:38:06Z) - Grounding Language with Visual Affordances over Unstructured Data [26.92329260907805]
We propose a novel approach to efficiently learn language-conditioned robot skills from unstructured, offline and reset-free data.
We exploit a self-supervised visuo-lingual affordance model, which requires as little as 1% of the total data with language.
We find that our method is capable of completing long-horizon, multi-tier tasks in the real world, while requiring an order of magnitude less data than previous approaches.
arXiv Detail & Related papers (2022-10-04T21:16:48Z) - Language Models as Zero-Shot Planners: Extracting Actionable Knowledge
for Embodied Agents [111.33545170562337]
We investigate the possibility of grounding high-level tasks, expressed in natural language, to a chosen set of actionable steps.
We find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into low-level plans.
We propose a procedure that conditions on existing demonstrations and semantically translates the plans to admissible actions.
arXiv Detail & Related papers (2022-01-18T18:59:45Z) - Ask Your Humans: Using Human Instructions to Improve Generalization in
Reinforcement Learning [32.82030512053361]
We propose the use of step-by-step human demonstrations in the form of natural language instructions and action trajectories.
We find that human demonstrations help solve the most complex tasks.
We also find that incorporating natural language allows the model to generalize to unseen tasks in a zero-shot setting.
arXiv Detail & Related papers (2020-11-01T14:39:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.