Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections

2022-11-18 · Frank Röder, Manfred Eppe

Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding methods for intelligent robots do not consider this. There exist numerous approaches considering non-understandings, but they ignore the incremental process of resolving misunderstandings. In this article, we present a first formalization and experimental validation of incremental action-repair for robotic instruction-following based on reinforcement learning. To evaluate our approach, we propose a collection of benchmark environments for action correction in language-conditioned reinforcement learning, utilizing a synthetic instructor to generate language goals and their corresponding corrections. We show that a reinforcement learning agent can successfully learn to understand incremental corrections of misunderstood instructions.

📄 PDF Abstract BibTeX arXiv:2211.10168

Code (1)

frankroeder/lanro-gym 공식 구현

Tasks

Instruction Following reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use

2026-01-31 · Minhua Lin, Enyan Dai, Hui Liu, Xianfeng Tang 외 arxiv

As Large Language Models (LLMs) are increasingly applied in high-stakes domains, their ability to reason strategically under uncertainty becomes critical. Poker provides a rigorous testbed, requiring not only strong acti…

Reinforcement Learning

Corpus of Cross-lingual Dialogues with Minutes and Detection of Misunderstandings

2025-12-23 · Marko Čechovič, Natália Komorníková, Dominik Macháček, Ondřej Bojar arxiv

Speech processing and translation technology have the potential to facilitate meetings of individuals who do not share any common language. To evaluate automatic systems for such a task, a versatile and realistic evaluat…

Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning

2020-11-01 · ICLR 2021 1 · Valerie Chen, Abhinav Gupta, Kenneth Marino

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-leve…

Multi-Task Learning reinforcement-learning Reinforcement Learning (RL)

VALAN: Vision and Language Agent Navigation

2019-12-06 · Larry Lansing, Vihan Jain, Harsh Mehta, Haoshuo Huang 외

VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded l…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

CRL-VLA: Continual Vision-Language-Action Learning

2026-02-03 · Qixin Zeng, Shuo Zhang, Hongyin Zhang, Renjie Wang 외 arxiv

Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterou…