Abstract
Robotic control via reinforcement learning (RL) has made significant advances. However, a serious weakness with this method is that RL models are prone to overfitting and have poor transfer performance. Transfer in reinforcement learning means that only a few samples are needed to train policy networks for new tasks. In this paper we investigate the problem of learning transferable policies for robots with serial structures, such as robotic arms, with the help of graph neural networks (GNN). The GNN was previously employed to incorporate explicitly the robot structure into the policy network, and thus make the policy easier to be generalized or transferred. Based on a kinematics analysis particularly on the serial robotic structure, in this paper we further improve the policy network by proposing a weighted information aggregation strategy. The experiment is conducted in a few-shot policy learning setting on a robotic arm. The experimental results show that the new aggregation strategy significantly improves the performance not only on the learning speed, but also on the policy accuracy.
This work is supported by National Key Research and Development Plan of China grant 2017YFB1300202, NSFC grants U1613213, 61375005, 61503383, 61210009, the Strategic Priority Research Program of Chinese Academy of Science under Grant XDB32050100, and Dongguan core technology research frontier project (2019622101001). The work is also supported by the Strategic Priority Research Program of the CAS (Grant XDB02080003).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ammar, H.B., Eaton, E., Ruvolo, P., Taylor, M.: Unsupervised cross-domain transfer for policy gradient reinforcement learning via manifold alignment. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
Ammar, H.B., Taylor, M.E.: Reinforcement learning transfer via common subspaces. In: Vrancx, P., Knudson, M., Grześ, M. (eds.) ALA 2011. LNCS (LNAI), vol. 7113, pp. 21–36. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-28499-1_2
Barabási, A.L., et al.: Network Science. Cambridge University Press, Cambridge (2016)
Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)
Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)
Chang, M.B., Ullman, T., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics. arXiv preprint arXiv:1612.00341 (2016)
Daftry, S., Bagnell, J.A., Hebert, M.: Learning transferable policies for monocular reactive MAV control. In: Kulić, D., Nakamura, Y., Khatib, O., Venture, G. (eds.) ISER 2016. SPAR, vol. 1, pp. 3–11. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-50115-4_1
Devin, C., Gupta, A., Darrell, T., Abbeel, P., Levine, S.: Learning modular neural network policies for multi-task and multi-robot transfer. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2169–2176. IEEE (2017)
Franco, S., Marco, G., Ah Chung, T., Markus, H., Gabriele, M.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61 (2009)
Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: IEEE International Conference on Robotics and Automation (2017)
Gupta, A., Devin, C., Liu, Y., Abbeel, P., Levine, S.: Learning invariant feature spaces to transfer skills with reinforcement learning. arXiv preprint arXiv:1703.02949 (2017)
Hamrick, J.B., et al.: Relational inductive bias for physical construction in humans and machines. arXiv preprint arXiv:1806.01203 (2018)
Hamrick, J.B., Ballard, A.J., Pascanu, R., Vinyals, O., Heess, N., Battaglia, P.W.: Metacontrol for adaptive imagination-based optimization. arXiv preprint arXiv:1705.02670 (2017)
Hoshen, Y.: VAIN: attentional multi-agent predictive modeling. In: Advances in Neural Information Processing Systems, pp. 2701–2711 (2017)
Kipf, T., Fetaya, E., Wang, K.C., Welling, M., Zemel, R.: Neural relational inference for interacting systems. arXiv preprint arXiv:1802.04687 (2018)
Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334–1373 (2015)
Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)
Metz, L., Ibarz, J., Jaitly, N., Davidson, J.: Discrete sequential prediction of continuous actions for deep RL. arXiv preprint arXiv:1705.05035 (2017)
Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)
Sanchez-Gonzalez, A., et al.: Graph networks as learnable physics engines for inference and control. arXiv preprint arXiv:1806.01242 (2018)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: Computational capabilities of graph neural networks. IEEE Trans. Neural Netw. 20(1), 81–102 (2008)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10(10), 1633–1685 (2009)
Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5026–5033. IEEE (2012)
Toyer, S., Trevizan, F., Thiébaux, S., Xie, L.: Action schema networks: generalised policies with deep learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Wang, T., Liao, R., Ba, J., Fidler, S.: NerveNet: learning structured policy with graph neural networks (2018)
Wilson, M., Spong, M.W.: Robot modeling and control. Ind. Robot Int. J. 17(5), 709–737 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, F., Xiong, F., Yang, X., Liu, Z. (2019). Learning Transferable Policies with Improved Graph Neural Networks on Serial Robotic Structure. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11955. Springer, Cham. https://doi.org/10.1007/978-3-030-36718-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-36718-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36717-6
Online ISBN: 978-3-030-36718-3
eBook Packages: Computer ScienceComputer Science (R0)