Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state- of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data- efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1801.01290 · Cited by 5,594
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“Prior work has shown that ordering tasks by heuristic measures of difficulty can be effective [45], [46].”
BackgroundDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“In the related field of supervised deep learning, transfer of knowledge by pre-training on a source task followed by finetuning on a target task [22], [23], [24] has been very successful in reducing the data requirements.”
BackgroundSelf-citationDomain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · cited 1×
“In RL settings, this idea has translated into domain randomization [31].”
MethodBetween MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Sutton, R. S., Precup, D., & Singh, S. (1999) · Artificial Intelligence · doi:10.1016/s0004-3702(99)00052-1 · Cited by 3,119
Learning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988
Rainbow: Combining Improvements in Deep Reinforcement Learning
Hessel, M., Modayil, J., Van Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M., & Silver, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11796 · Cited by 1,846
Curiosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815 · cited 1×
“using better optimization methods [9], [10], [11], combining model-based and model-free learning [12], hierarchical learning [13], and design of better exploration methods [14], [15], [16], [17], [18].”
MethodSelf-citation
Cited by
A Survey on Deep Reinforcement Learning Algorithms for Robotic Manipulation
Han, D., Mulyana, B., Stankovic, V., & Cheng, S. (2023) · Sensors · doi:10.3390/s23073762 · Cited by 253
“Towards practical multi-object manipulation using relational reinforcement learning [66] SAC and HER Sequential curriculum learning”
BackgroundMethodManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Mu, T., Ling, Z., Xiang, F., Yang, D., Li, X., Tao, S., Huang, Z., Jia, Z., & Su, H. (2021) · arXiv · doi:10.48550/arxiv.2107.14483 · Cited by 34
“Recently, reinforcement learning and imitation learning show success in learning object grasping [36] and manipulation [37, 13, 14, 15, 38, 16, 39, 40].”
BackgroundCounterfactual Data Augmentation using Locally Factored Dynamics
Pitis, S., Creager, E., & Garg, A. (2020) · arXiv · doi:10.48550/arxiv.2007.02863 · Cited by 26
Asymmetric self-play for automatic goal discovery in robotic manipulation
OpenAI, O., Plappert, M., Sampedro, R., Xu, T., Akkaya, I., Kosaraju, V., Welinder, P., D'Sa, R., Petron, A., Pinto, H. P. D. O., et al. (2021) · arXiv · doi:10.48550/arxiv.2101.04882 · Cited by 18
“Learning block stacking often requires a hand-designed curriculum (Li et al., 2019), meticulous reward shaping (Popov et al.”
Background
Metadata
- Authors
- Li, R., Jabri, A., Darrell, T., & Agrawal, P.
- Venue
- 2020 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 4051-4058
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W3089482831
- Cited by
- 78
- References
- 21
- FWCI
- 5.85
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning. https://app.cochat.ai/papers/10.1109/icra40945.2020.9197468
- The paper
- Li, R., Jabri, A., Darrell, T., & Agrawal, P. (2020). Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning. 2020 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra40945.2020.9197468
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.