mlsanityData to 7 Oct 2026

Language-Conditioned Offline RL for Multi-Robot Navigation

arXiv 2407.20164 ↗First posted 29 Jul 2024cs.RO cs.AI cs.LGcited by 9

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

We present a method for developing navigation policies for multi-robot teams that interpret and follow natural language instructions. We condition these policies on embeddings from pretrained Large Language Models (LLMs), and train them via offline reinforcement learning with as little as 20 minutes of randomly-collected data. Experiments on a team of five real robots show that these policies generalize well to unseen commands, indicating an understanding of the LLM latent space. Our method requires no simulators or environment models, and produces low-latency control policies that can be deployed directly to real robots without finetuning. We provide videos of our experiments at https://sites.google.com/view/llm-marl.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 45 of its 57 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

45 of 57 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2016Layer Normalizationcited by 5,579
  7. 2015Continuous control with deep reinforcement learningcited by 3,279
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  9. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  11. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  12. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
33 more
  1. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  4. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  6. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  7. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  8. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  9. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  10. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  11. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  12. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  13. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  14. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  15. 2023Efficient Online Reinforcement Learning with Offline Datacited by 332
  16. 2023Improving Text Embeddings with Large Language Modelscited by 295
  17. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  18. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  19. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 231
  20. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  21. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
  22. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  23. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 151
  24. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 145
  25. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 104
  26. 2023AnglE-optimized Text Embeddingscited by 98
  27. 2021Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learningcited by 78
  28. 2023Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigationcited by 74
  29. 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 63
  30. 2023Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learningcited by 36
  31. 2021Regularized Softmax Deep Multi-Agent Q-Learningcited by 19
  32. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11
  33. 2024The Cambridge RoboMaster: An Agile Multi-Robot Research Platformcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2025Large Language Models for Multi-Robot Systems: A Surveycited by 26
  2. 2024MARLIN: Multi-Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiationcited by 5
  3. 2026A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Datacited by 5
  4. 2025Data-Efficient Multi-Agent Spatial Planning with LLMscited by 3
  5. 2025Sight Over Site: Perception-Aware Reinforcement Learning for Efficient Robotic Inspectioncited by 1
  6. 2025ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Controlcited by 0
  7. 2025MindFlow+: A Self-Evolving Agent for E-Commerce Customer Servicecited by 0
  8. 2025Prompting Robot Teams with Natural Languagecited by 0
  9. 2026A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents
  2. 2025LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning
  3. 2025ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts
  4. 2023Conditionally Combining Robot Skills using Large Language Models
  5. 2023Towards A Unified Agent with Foundation Models
  6. 2026Adapting Generalist Robot Policies with Semantic Reinforcement Learning
  7. 2015Learning Models for Following Natural Language Directions in Unknown Environments
  8. 2024Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation