paper-with-me

Papers

Policy Improvement using Language Feedback Models

2024-02-12 · Victor Zhong, Dipendra Misra, Xingdi Yuan, Marc-Alexandre Côté

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large Language Models (LLMs) on visual trajectories verbalized to language descriptions. First, by using LFMs to identify desirable behaviour to imitate, we improve in task-completion rate over strong behavioural cloning baselines on three distinct language grounding environments (Touchdown, ScienceWorld, and ALFWorld). Second, LFMs outperform using LLMs as experts to directly predict actions, when controlling for the number of LLM output tokens. Third, LFMs generalize to unseen environments, improving task-completion rate by 3.5-12.0% through one round of adaptation. Finally, LFM can be modified to provide human-interpretable feedback without performance loss, allowing human verification of desirable behaviour for imitation learning.

📄 PDF Abstract BibTeX arXiv:2402.07876

Code (1)

vzhong/language_feedback_models 공식 구현 pytorch

Tasks

Behavioural cloningImitation LearningInstruction Following

Similar Papers 제목 키워드 기반

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

2026-05-29 · Xiaobo Wang, Tong Wu, Min Tang, Jiaqi Li 외 arxiv

Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference data from human annotation or judge models. It is dramatically wors…

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

2026-05-13 · Junjie Zhang, Guozheng Ma, Shunyu Liu, Zetian Hu 외 arxiv

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations …

Reinforcement Learning

Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback

2026-06-12 · Woohyeon Byeon, Jiwon Jeon, Jeonghye Kim, Youngchul Sung arxiv

We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback. Unlike one-way distillation or single-model fine-tuning, our goal …

Policy Improvement Reinforcement Learning

2026-04-01 · Huaiyang Wang, Xiaojie Li, Xiaohan Wang, Zhixia Zhang 외 arxiv

Reinforcement learning has become a central post-training paradigm for improving LLM and agent capabilities. Yet existing RL post-training methods share a common blind spot: they construct local learning signals from sam…

Mathematical ReasoningReinforcement Learning

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

2026-03-23 · Dmitrii Plotnikov, Iaroslav Kolomiets, Dmitrii Maliukov, Dmitrij Kosenkov 외 arxiv

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that …

Reinforcement Learning