Pith. sign in

REVIEW 2 cited by

Large Language Models as Generalizable Policies for Embodied Tasks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.17722 v2 pith:7MRZKIGA submitted 2023-10-26 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords languagetasksllarpembodiedinstructionslargerearrangementgeneralizable
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A single MLLM-based agent, finetuned with cross-domain supervision and online RL, achieves strong zero-shot generalization across manipulation, navigation, games, UI control, and planning.

  2. TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making

    cs.AI 2025-09 conditional novelty 5.0 of 10

    TCPO uses stepwise preference optimization and an action consistency constraint to raise ALFWorld average success from 20.0% to 26.7%.

Pith tools