mlsanityData to 14 Oct 2026

SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling

arXiv 2306.11886 ↗First posted 20 Jun 2023cs.RO cs.AI cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-trajectory skill chaining through offline reinforcement learning. As a result, SPRINT pre-training equips robots with a much richer repertoire of skills. Experimental results in a household simulator and on a real robot kitchen manipulation task show that SPRINT leads to substantially faster learning of new long-horizon tasks than previous pre-training approaches. Website at https://clvrai.com/sprint.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 57 of its 80 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

57 of 80 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  9. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  11. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
38 more
  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  4. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  5. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  6. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  7. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  8. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  9. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 782
  10. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  11. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  12. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 671
  13. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  14. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  15. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  16. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  17. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  18. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  19. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 384
  20. 2019Learning Latent Plans from Playcited by 316
  21. 2019Dynamics-Aware Unsupervised Discovery of Skillscited by 313
  22. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
  23. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  24. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  25. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221
  26. 2022Interactive Language: Talking to Robots in Real Timecited by 218
  27. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 209
  28. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  29. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 177
  30. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 166
  31. 2021Episodic Transformer for Vision-and-Language Navigationcited by 156
  32. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 138
  33. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 138
  34. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
  35. 2021Discovering and Achieving Goals via World Modelscited by 131
  36. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
  37. 2018Variational Option Discovery Algorithmscited by 122
  38. 2023GenAug: Retargeting behaviors to unseen situations via Generative Augmentationcited by 104

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 9; 2025: 4; 2026: 7.

24 papers.

Sort:

By area:

  1. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 110
  2. 2023Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidancecited by 86
  3. 2023TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Modelscited by 53
  4. 2024RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulationcited by 43
  5. 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
  6. 2026Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Controlcited by 20
  7. 2024MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulationcited by 19
  8. 2024Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitationcited by 18
  9. 2023LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teacherscited by 14
  10. 2024Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Modelscited by 14
  11. 2024STEER: Flexible Robotic Manipulation via Dense Language Groundingcited by 14
  12. 2024EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Datacited by 13
12 more
  1. 2025PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policiescited by 12
  2. 2024Language-guided Skill Learning with Temporal Variational Inferencecited by 11
  3. 2024ING-VP: MLLMs cannot Play Easy Vision-based Games Yetcited by 11
  4. 2025BOSS: Benchmark for Observation Space Shift in Long-Horizon Taskcited by 7
  5. 2026Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progresscited by 6
  6. 2025Learning Skills from Action-Free Videoscited by 3
  7. 2026TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuningcited by 3
  8. 2025Reward Generation via Large Vision-Language Model in Offline Reinforcement Learningcited by 2
  9. 2026Task Robustness via Re-Labelling Vision-Action Robot Datacited by 2
  10. 2026Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skillscited by 1
  11. 2026Learning More from Less: Reinforcement Learning from Hindsightcited by 0
  12. 2026Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
  2. 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
  3. 2026From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
  4. 2024Training Fast Robot Policies with Slow Foundation Models
  5. 2024Yell At Your Robot: Improving On-the-Fly from Language Corrections
  6. 2025SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning
  7. 2025ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
  8. 2023Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning