Learning agile soccer skills for a bipedal robot with deep reinforcement learning
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
We investigated whether deep reinforcement learning (deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies. We used deep RL to train a humanoid robot to play a simplified one-versus-one soccer game. The resulting agent exhibits robust and dynamic movement skills, such as rapid fall recovery, walking, turning, and kicking, and it transitions between them in a smooth and efficient manner. It also learned to anticipate ball movements and block opponent shots. The agent’s tactical behavior adapts to specific game contexts in a way that would be impractical to manually design. Our agent was trained in simulation and transferred to real robots zero-shot. A combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training enabled good-quality transfer. In experiments, the agent walked 181% faster, turned 302% faster, took 63% less time to get up, and kicked a ball 34% faster than a scripted baseline.
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
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101
NeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Vinyals, O., Babuschkin, I., Czarnecki, W. M., Mathieu, M., Dudzik, A., Chung, J., Choi, D. H., Powell, R., Ewalds, T., Georgiev, P., et al. (2019) · Nature · doi:10.1038/s41586-019-1724-z · Cited by 3,455
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160
Between 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
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Ross, S., Gordon, G. J., & Bagnell, J. A. (2018) · Carnegie Mellon University · doi:10.1184/r1/6550949 · Cited by 1,941
Learning agile and dynamic motor skills for legged robots
Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V., & Hutter, M. (2019) · Science Robotics · doi:10.1126/scirobotics.aau5872 · Cited by 1,482
Learning quadrupedal locomotion over challenging terrain
Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., & Hutter, M. (2020) · Science Robotics · doi:10.1126/scirobotics.abc5986 · Cited by 1,156
Sims, K. (1994) · Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94 · doi:10.1145/192161.192167 · Cited by 1,005 · cited 1×
“Attempts at creating intelligent embodied agents with sophisticated motor capabilities go back many years, both in simulation [1] and in the real world [2, 3].”
BackgroundReinforcement learning of motor skills with policy gradients
Peters, J., & Schaal, S. (2008) · Neural Networks · doi:10.1016/j.neunet.2008.02.003 · Cited by 831
Emergence of Locomotion Behaviours in Rich Environments
Heess, N., TB, D., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., Eslami, S. M. A., et al. (2017) · arXiv · doi:10.48550/arxiv.1707.02286 · Cited by 657
Self-citationHow to train your robot with deep reinforcement learning: Lessons we have learned
Ibarz, J., Tan, J., Finn, C., Kalakrishnan, M., Pastor, P., & Levine, S. (2021) · The International Journal of Robotics Research · doi:10.1177/0278364920987859 · Cited by 570
Tassa, Y., Doron, Y., Muldal, A., Erez, T., Li, Y., Casas, D. D. L., Budden, D., Abdolmaleki, A., Merel, J., Lefrancq, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1801.00690 · Cited by 497 · cited 1×
“In both the simulated and real environments, the pitch is bordered by ramps, which ensures that the ball returns to the bounds of the pitch.”
BackgroundSelf-citationA Survey of Multi-Objective Sequential Decision-Making
Roijers, D. M., Vamplew, P., Whiteson, S., & Dazeley, R. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3987 · Cited by 461 · cited 1×
“However, multi-objective RL [70, 71] or constrained RL [72] might be able to obtain better solutions.”
BackgroundLearning to Walk Via Deep Reinforcement Learning
Haarnoja, T., Ha, S., Zhou, A., Tan, J., Tucker, G., & Levine, S. (2019) · Robotics: Science and Systems XV · doi:10.15607/rss.2019.xv.011 · Cited by 430
Self-citationEmergent Tool Use From Multi-Agent Autocurricula
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., & Mordatch, I. (2019) · arXiv · doi:10.48550/arxiv.1909.07528 · Cited by 424
Learning Agile Robotic Locomotion Skills by Imitating Animals
Bin Peng, X., Coumans, E., Zhang, T., Lee, T.-W., Tan, J., & Levine, S. (2020) · Robotics: Science and Systems XVI · doi:10.15607/rss.2020.xvi.064 · Cited by 357
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
Lanctot, M., Zambaldi, V., Gruslys, A., Lazaridou, A., Tuyls, K., Perolat, J., Silver, D., & Graepel, T. (2017) · arXiv · doi:10.48550/arxiv.1711.00832 · Cited by 295
Rusu, A. A., Colmenarejo, S. G., Gulcehre, C., Desjardins, G., Kirkpatrick, J., Pascanu, R., Mnih, V., Kavukcuoglu, K., & Hadsell, R. (2015) · arXiv · doi:10.48550/arxiv.1511.06295 · Cited by 270
Self-citationMaximum a Posteriori Policy Optimisation
Abdolmaleki, A., Springenberg, J. T., Tassa, Y., Munos, R., Heess, N., & Riedmiller, M. (2018) · arXiv · doi:10.48550/arxiv.1806.06920 · Cited by 259
Self-citationBlind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning
Siekmann, J., Green, K., Warila, J., Fern, A., & Hurst, J. (2021) · arXiv · doi:10.48550/arxiv.2105.08328 · Cited by 193
Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning
Siekmann, J., Green, K., Warila, J., Fern, A., & Hurst, J. (2021) · Robotics: Science and Systems XVII · doi:10.15607/rss.2021.xvii.061 · Cited by 193
Robot Learning From Randomized Simulations: A Review
Muratore, F., Ramos, F., Turk, G., Yu, W., Gienger, M., & Peters, J. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.799893 · Cited by 128 · cited 2×
“A common theme is that a surprisingly small number of techniques can be sufficient to reduce the sim-to-real gap[37, 43], which is also supported by our results.”
MethodResultThe manifold structure of limb coordination in walking Drosophila
DeAngelis, B. D., Zavatone-Veth, J. A., & Clark, D. A. (2019) · eLife · doi:10.7554/elife.46409 · Cited by 104 · cited 1×
“We also ablated the use of self-play in the second stage, while keeping the skill policy regularization and the shaped reward the same.”
MethodFrom motor control to team play in simulated humanoid football
Liu, S., Lever, G., Wang, Z., Merel, J., Eslami, S. M. A., Hennes, D., Czarnecki, W. M., Tassa, Y., Omidshafiei, S., Abdolmaleki, A., et al. (2022) · Science Robotics · doi:10.1126/scirobotics.abo0235 · Cited by 88
Self-citationOpen-ended Learning in Symmetric Zero-sum Games
Balduzzi, D., Garnelo, M., Bachrach, Y., Czarnecki, W. M., Perolat, J., Jaderberg, M., & Graepel, T. (2019) · arXiv · doi:10.48550/arxiv.1901.08106 · Cited by 88
Legged Locomotion in Challenging Terrains using Egocentric Vision
Agarwal, A., Kumar, A., Malik, J., & Pathak, D. (2022) · arXiv · doi:10.48550/arxiv.2211.07638 · Cited by 82 · cited 1×
“For example, Lee et al. [12] applied zero-shot sim-to-real deep RL to deploy learned locomotion policies in natural environments, including mud, snow, vegetation, and streaming water.”
BackgroundDayDreamer: World Models for Physical Robot Learning
Wu, P., Escontrela, A., Hafner, D., Goldberg, K., & Abbeel, P. (2022) · arXiv · doi:10.48550/arxiv.2206.14176 · Cited by 76
Kickstarting Deep Reinforcement Learning
Schmitt, S., Hudson, J. J., Zidek, A., Osindero, S., Doersch, C., Czarnecki, W. M., Leibo, J. Z., Kuttler, H., Zisserman, A., Simonyan, K., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.03835 · Cited by 67
Multi-agent manipulation via locomotion using hierarchical sim2real
Nachum, O., Ahn, M., Ponte, H., Gu, S., & Kumar, V. (2019) · arXiv · doi:10.48550/arxiv.1908.05224 · Cited by 46
Metadata
- Authors
- Haarnoja, T., Moran, B., Lever, G., Huang, S. H., Tirumala, D., Humplik, J., Wulfmeier, M., Tunyasuvunakool, S., Siegel, N. Y., Hafner, R., Bloesch, M., Hartikainen, K., Byravan, A., Hasenclever, L., Tassa, Y., Sadeghi, F., Batchelor, N., Casarini, F., Saliceti, S., Game, C., Sreendra, N., Patel, K., Gwira, M., Huber, A., Hurley, N., Nori, F., Hadsell, R., & Heess, N.
- Venue
- Science Robotics
- Published
- 2024-04-10
- Volume
- 9
- Issue
- 89
- Pages
- eadi8022-eadi8022
- ISSN
- 2470-9476 (ISSN-L)
- OpenAlex
- W4394674699
- Cited by
- 173
- References
- 32
- FWCI
- 25.30
- Type
- journal article
- 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
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.