CoChat
Sign Up
Cited by 135Reinforcement Learning in RoboticsRobot Manipulation and LearningDomain Adaptation and Few-Shot Learning

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

Open access
Liu, Bo, Zhu, Yifeng, Gao, Chongkai, Feng, Yihao, Liu, Qiang, Zhu, Yuke, Stone, Peter·2023·Advances in Neural Information Processing Systems 36
DOI 10.52202/075280-1939
Open this paper in CoChat — free accountOpen PDF

Abstract

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and concepts, lifelong learning in decision-making (LLDM) also necessitates the transfer of procedural knowledge, such as actions and behaviors. To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation. Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks. For benchmarking purpose, we create four task suites (130 tasks in total) that we use to investigate the above-mentioned research topics. To support sample-efficient learning, we provide high-quality human-teleoperated demonstration data for all tasks. Our extensive experiments present several insightful or even unexpected discoveries: sequential finetuning outperforms existing lifelong learning methods in forward transfer, no single visual encoder architecture excels at all types of knowledge transfer, and naive supervised pretraining can hinder agents' performance in the subsequent LLDM. Check the website at https://libero-project.github.io for the code and the datasets.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.52202/075280-1939

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • LIBERO proposes four fixed task suites with 10 tasks each.

    “While accomodating for procedural task generation, LIBERO proposes four fixed task suites with 10 tasks each researchers can benchmark on.”

    From LeRobot: An Open-Source Library for End-to-End Robot Learning (2026) · cites this paper as Liu et al., 2023

    Section 4.2 (Task Suites) confirms that LIBERO offers four fixed suites for benchmarking. It says LIBERO-SPATIAL, LIBERO-OBJECT, and LIBERO-GOAL have 10 tasks each, but the fourth suite, LIBERO-100, has 100 tasks—not 10. (LLM, conf=0.94)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Part of this paper’s reference list could not be split into single entries.

Research works printed but not linked: 71

  1. [1][1] Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Yoshua Bengio, Bern- hard Schölkopf, Manuel Wüthrich, and Stefan Bauer. Causalworld: A robotic manipulation benchmark for causal structure and transfer learning. arXiv preprint arXiv:2010.04296, 2020. · arXiv
  2. [2][2] Ali Ayub and Carter Fendley. Few-shot continual active learning by a robot. arXiv preprint arXiv:2210.04137, 2022. · arXiv
  3. [3][3] Ali Ayub and Alan R Wagner. F-siol-310: A robotic dataset and benchmark for few-shot incre- mental object learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 13496–13502. IEEE, 2021. 10
  4. [4][4] Michael Bain and Claude Sammut. A framework for behavioural cloning. In Machine Intelli- gence 15, pages 103–129, 1995.
  5. [5][5] Eseoghene Ben-Iwhiwhu, Saptarshi Nath, Praveen K Pilly, Soheil Kolouri, and Andrea Soltog- gio. Lifelong reinforcement learning with modulating masks. arXiv preprint arXiv:2212.11110, 2022. · arXiv
  6. [6][6] Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pages 41–48, 2009.
  7. [7][7] Magdalena Biesialska, Katarzyna Biesialska, and Marta R Costa-Jussa. Continual lifelong learning in natural language processing: A survey. arXiv preprint arXiv:2012.09823, 2020. · arXiv
  8. [9][9] Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and Simone Calderara. Dark experience for general continual learning: a strong, simple baseline. Advances in neural information processing systems, 33:15920–15930, 2020.
  9. [10][10] Rich Caruana. Multitask learning. Machine learning, 28(1):41–75, 1997.
  10. [11][11] Arslan Chaudhry, Puneet K Dokania, Thalaiyasingam Ajanthan, and Philip HS Torr. Riemannian walk for incremental learning: Understanding forgetting and intransigence. In Proceedings of the European Conference on Computer Vision (ECCV), pages 532–547, 2018.
  11. [12][12] Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420, 2018. · arXiv
  12. [13][13] Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K Dokania, Philip HS Torr, and Marc'Aurelio Ranzato. On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486, 2019. · arXiv
  13. [14][14] Brian Cheung, Alexander Terekhov, Yubei Chen, Pulkit Agrawal, and Bruno Olshausen. Su- perposition of many models into one. Advances in neural information processing systems, 32, 2019.
  14. [15][15] Karl Cobbe, Chris Hesse, Jacob Hilton, and John Schulman. Leveraging procedural generation to benchmark reinforcement learning. In International conference on machine learning, pages 2048–2056. PMLR, 2020.
  15. [16][16] Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Aleš Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7):3366– 3385, 2021.
  16. [17][17] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large- scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  17. [18][18] Li Deng. The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine, 29(6):141–142, 2012.
  18. [19][19] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. · arXiv
  19. [20][20] Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, and Davide Maltoni. Don't forget, there is more than forgetting: new metrics for continual learning. arXiv preprint arXiv:1810.13166, 2018. · arXiv
  20. [22][22] Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, et al. Ego4d: Around the world in 3,000 hours of egocentric video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18995–19012, 2022.
  21. [23][23] Sam Greydanus, Anurag Koul, Jonathan Dodge, and Alan Fern. Visualizing and understanding atari agents. ArXiv, abs/1711.00138, 2017. · arXiv
  22. [24][24] Jiayuan Gu, Fanbo Xiang, Xuanlin Li, Zhan Ling, Xiqiang Liu, Tongzhou Mu, Yihe Tang, Stone Tao, Xinyue Wei, Yunchao Yao, et al. Maniskill2: A unified benchmark for generalizable manipulation skills. arXiv preprint arXiv:2302.04659, 2023. · arXiv
  23. [25][25] Matthew Hausknecht and Peter Stone. Deep recurrent q-learning for partially observable mdps. In 2015 aaai fall symposium series, 2015.
  24. [26][26] Ching-Yi Hung, Cheng-Hao Tu, Cheng-En Wu, Chien-Hung Chen, Yi-Ming Chan, and Chu- Song Chen. Compacting, picking and growing for unforgetting continual learning. Advances in Neural Information Processing Systems, 32, 2019.
  25. [27][27] Stephen James, Zicong Ma, David Rovick Arrojo, and Andrew J Davison. Rlbench: The robot learning benchmark & learning environment. IEEE Robotics and Automation Letters, 5(2):3019–3026, 2020.
  26. [28][28] Leslie Pack Kaelbling. The foundation of efficient robot learning. Science, 369(6506):915–916, 2020.
  27. [29][29] Minsoo Kang, Jaeyoo Park, and Bohyung Han. Class-incremental learning by knowledge distillation with adaptive feature consolidation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16071–16080, 2022.
  28. [30][30] Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, and Wojciech Jaśkowski. Vizdoom: A doom-based ai research platform for visual reinforcement learning. In 2016 IEEE conference on computational intelligence and games (CIG), pages 1–8. IEEE, 2016.
  29. [31][31] Wonjae Kim, Bokyung Son, and Ildoo Kim. Vilt: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning, pages 5583–5594. PMLR, 2021.
  30. [32][32] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. · arXiv
  31. [33][33] James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.
  32. [35][35] Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Martín- Martín, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun, et al. Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In Conference on Robot Learning, pages 80–93. PMLR, 2023.
  33. [37][37] Hao Liu and Huaping Liu. Continual learning with recursive gradient optimization. arXiv preprint arXiv:2201.12522, 2022. · arXiv
  34. [38][38] Vincenzo Lomonaco and Davide Maltoni. Core50: a new dataset and benchmark for continuous object recognition. In Conference on Robot Learning, pages 17–26. PMLR, 2017.
  35. [39][39] David Lopez-Paz and Marc'Aurelio Ranzato. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30, 2017. 12
  36. [41][41] Arun Mallya and Svetlana Lazebnik. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 7765–7773, 2018.
  37. [42][42] Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, and Roberto Martín-Martín. What matters in learning from offline human demonstrations for robot manipulation. arXiv preprint arXiv:2108.03298, 2021. · arXiv
  38. [44][44] Jorge A Mendez, Marcel Hussing, Meghna Gummadi, and Eric Eaton. Composuite: A compo- sitional reinforcement learning benchmark. arXiv preprint arXiv:2207.04136, 2022. · arXiv
  39. [45][45] Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, and Mehrdad Farajtabar. Architecture matters in continual learning. arXiv preprint arXiv:2202.00275, 2022. · arXiv
  40. [46][46] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013. · arXiv
  41. [47][47] Tongzhou Mu, Zhan Ling, Fanbo Xiang, Derek Yang, Xuanlin Li, Stone Tao, Zhiao Huang, Zhiwei Jia, and Hao Su. Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations. arXiv preprint arXiv:2107.14483, 2021. · arXiv
  42. [48][48] Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E Taylor, and Peter Stone. Curriculum learning for reinforcement learning domains: A framework and survey. arXiv preprint arXiv:2003.04960, 2020. · arXiv
  43. [49][49] German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. Continual lifelong learning with neural networks: A review. Neural Networks, 113:54–71, 2019.
  44. [50][50] Ethan Perez, Florian Strub, Harm De Vries, Vincent Dumoulin, and Aaron Courville. Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
  45. [51][51] Sam Powers, Eliot Xing, Eric Kolve, Roozbeh Mottaghi, and Abhinav Gupta. Cora: Benchmarks, baselines, and metrics as a platform for continual reinforcement learning agents. arXiv preprint arXiv:2110.10067, 2021. · arXiv
  46. [52][52] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  47. [53][53] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.
  48. [54][54] Amanda Rios and Laurent Itti. Lifelong learning without a task oracle. In 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pages 255–263. IEEE, 2020.
  49. [55][55] Stéphane Ross, Geoffrey Gordon, and Drew Bagnell. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth interna- tional conference on artificial intelligence and statistics, pages 627–635. JMLR Workshop and Conference Proceedings, 2011. 13
  50. [56][56] Andrei A Rusu, Neil C Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. Progressive neural networks. arXiv preprint arXiv:1606.04671, 2016. · arXiv
  51. [57][57] Gobinda Saha, Isha Garg, Aayush Ankit, and Kaushik Roy. Space: Structured compression and sharing of representational space for continual learning. IEEE Access, 9:150480–150494, 2021.
  52. [58][58] Mikayel Samvelyan, Robert Kirk, Vitaly Kurin, Jack Parker-Holder, Minqi Jiang, Eric Hambro, Fabio Petroni, Heinrich Küttler, Edward Grefenstette, and Tim Rocktäschel. Minihack the planet: A sandbox for open-ended reinforcement learning research. arXiv preprint arXiv:2109.13202, 2021. · arXiv
  53. [59][59] Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich. Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4938–4947, 2020.
  54. [60][60] Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, and Raia Hadsell. Progress & compress: A scalable framework for continual learning. In International Conference on Machine Learning, pages 4528–4537. PMLR, 2018.
  55. [61][61] Qi She, Fan Feng, Xinyue Hao, Qihan Yang, Chuanlin Lan, Vincenzo Lomonaco, Xuesong Shi, Zhengwei Wang, Yao Guo, Yimin Zhang, et al. Openloris-object: A robotic vision dataset and benchmark for lifelong deep learning. In 2020 IEEE international conference on robotics and automation (ICRA), pages 4767–4773. IEEE, 2020.
  56. [62][62] Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mot- taghi, Luke Zettlemoyer, and Dieter Fox. Alfred: A benchmark for interpreting grounded instructions for everyday tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10740–10749, 2020.
  57. [63][63] Sanjana Srivastava, Chengshu Li, Michael Lingelbach, Roberto Martín-Martín, Fei Xia, Kent El- liott Vainio, Zheng Lian, Cem Gokmen, Shyamal Buch, Karen Liu, et al. Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments. In Conference on Robot Learning, pages 477–490. PMLR, 2022.
  58. [64][64] Open Ended Learning Team, Adam Stooke, Anuj Mahajan, Catarina Barros, Charlie Deck, Jakob Bauer, Jakub Sygnowski, Maja Trebacz, Max Jaderberg, Michael Mathieu, et al. Open- ended learning leads to generally capable agents. arXiv preprint arXiv:2107.12808, 2021. · arXiv
  59. [65][65] Sebastian Thrun and Tom M Mitchell. Lifelong robot learning. Robotics and autonomous systems, 15(1-2):25–46, 1995.
  60. [66][66] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  61. [67][67] Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461, 2018. · arXiv
  62. [68][68] Chen Wang, Linxi Fan, Jiankai Sun, Ruohan Zhang, Li Fei-Fei, Danfei Xu, Yuke Zhu, and Anima Anandkumar. Mimicplay: Long-horizon imitation learning by watching human play. arXiv preprint arXiv:2302.12422, 2023. · arXiv
  63. [69][69] Maciej Wołczyk, Michal Zajkac, Razvan Pascanu, Lukasz Kuci'nski, and Piotr Milo's. Continual world: A robotic benchmark for continual reinforcement learning. In Neural Information Processing Systems, 2021.
  64. [70][70] Maciej Wołczyk, Michal Zajkac, Razvan Pascanu, Lukasz Kuci'nski, and Piotr Milo's. Disen- tangling transfer in continual reinforcement learning. ArXiv, abs/2209.13900, 2022. 14 · arXiv
  65. [71][71] Lemeng Wu, Bo Liu, Peter Stone, and Qiang Liu. Firefly neural architecture descent: a general approach for growing neural networks. Advances in Neural Information Processing Systems, 33:22373–22383, 2020.
  66. [72][72] Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang. Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547, 2017. · arXiv
  67. [73][73] Tianhe Yu, Deirdre Quillen, Zhanpeng He, Ryan Julian, Karol Hausman, Chelsea Finn, and Sergey Levine. Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning. In Conference on robot learning, pages 1094–1100. PMLR, 2020.
  68. [74][74] Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, Shiliang Pu, and De-Chuan Zhan. Forward compatible few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9046–9056, 2022.
  69. [75][75] Yifeng Zhu, Abhishek Joshi, Peter Stone, and Yuke Zhu. Viola: Imitation learning for vision- based manipulation with object proposal priors. arXiv preprint arXiv:2210.11339, 2022. · arXiv
  70. [76][76] Yuke Zhu, Josiah Wong, Ajay Mandlekar, and Roberto Martín-Martín. robosuite: A modular simulation framework and benchmark for robot learning. arXiv preprint arXiv:2009.12293, 2020. 15 Checklist · arXiv
  71. [1]1. For all authors... (a) Do the main claims made in the abstract and introduction accurately reflect the paper's contributions and scope? [Yes] (b) Did you describe the limitations of your work? [Yes] (c) Did you discuss any potential negative societal impacts of your work? [Yes] (d) Have you read the ethics review guidelines and ensured that your paper conforms to them? [Yes]

Cited by

Sorted by citations

Authors
Liu, B., Zhu, Y., Gao, C., Feng, Y., Liu, Q., Zhu, Y., & Stone, P.
ORCID
Zhu, Yuke
Venue
Advances in Neural Information Processing Systems 36
Publisher
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Published
2023
Pages
44776-44791
ISSN
1049-5258 (ISSN-L)
DOI
10.52202/075280-1939
OpenAlex
W7133220882
Cited by
135
References
0
Citations by year
2026: 114 · 2025: 18 · 2024: 3
FWCI
23.92
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • neural information processing systems (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
knowledge transfer, benchmarking, robot learning, transfer learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review