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
Signed reviews
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.
Forward citations
Cited by 2 Pith papers
-
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
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.
-
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making
TCPO uses stepwise preference optimization and an action consistency constraint to raise ALFWorld average success from 20.0% to 26.7%.
Discussion (0). Continue with ORCID to comment.