Sparse representation learning with modified q-VAE towards minimal realization of world model

References

• Sanchez J, Corrales JA, Bouzgarrou BC, et al. Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey. Int J Rob Res. 2018;37(7):688–716. doi: 10.1177/0278364918779698
   Web of Science ®Google Scholar
• Tsurumine Y, Cui Y, Uchibe E, et al. Deep reinforcement learning with smooth policy update: application to robotic cloth manipulation. Rob Auton Syst. 2019;112:72–83. doi: 10.1016/j.robot.2018.11.004
   Web of Science ®Google Scholar
• Modares H, Ranatunga I, Lewis FL, et al. Optimized assistive human–robot interaction using reinforcement learning. IEEE Trans Cybern. 2015;46(3):655–667. doi: 10.1109/TCYB.2015.2412554
   PubMed Web of Science ®Google Scholar
• Kobayashi T, Dean-Leon E, Guadarrama-Olvera JR, et al. Whole-body multicontact haptic human–humanoid interaction based on leader–follower switching: a robot dance of the ‘box step’. Adv Intell Syst. 2022;4(2):2100038. doi: 10.1002/aisy.v4.2
   Google Scholar
• Paden B, Čáp M, Yong SZ, et al. A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Trans Intell Veh. 2016;1(1):33–55. doi: 10.1109/TIV.2016.2578706
   Google Scholar
• Williams G, Drews P, Goldfain B, et al. Information-theoretic model predictive control: theory and applications to autonomous driving. IEEE Trans Robot. 2018;34(6):1603–1622. doi: 10.1109/TRO.8860
   Web of Science ®Google Scholar
• Botev ZI, Kroese DP, Rubinstein RY, et al. The cross-entropy method for optimization. In: Handbook of statistics. Vol. 31. Elsevier; 2013. p. 35–59.
   Google Scholar
• Ha D, Schmidhuber J. World models; 2018. arXiv preprint arXiv:180310122.
   Google Scholar
• Hafner D, Lillicrap T, Ba J, et al. Dream to control: learning behaviors by latent imagination. In: International Conference on Learning Representations; 2020.
   Google Scholar
• Hafner D, Lillicrap TP, Norouzi M, et al. Mastering atari with discrete world models. In: International Conference on Learning Representations; 2021.
   Google Scholar
• Okada M, Kosaka N, Taniguchi T. Planet of the bayesians: reconsidering and improving deep planning network by incorporating bayesian inference. In: IEEE/RSJ International Conference on Intelligent Robots and Systems; IEEE; 2020. p. 5611–5618.
   Google Scholar
• Okada M, Taniguchi T. Dreaming: model-based reinforcement learning by latent imagination without reconstruction. In: IEEE International Conference on Robotics and Automation; IEEE; 2021. p. 4209–4215.
   Google Scholar
• Kingma DP, Welling M. Auto-encoding variational bayes. In: International Conference on Learning Representations; 2014.
   Google Scholar
• Higgins I, Matthey L, Pal A, et al. beta-vae: learning basic visual concepts with a constrained variational framework. In: International Conference on Learning Representations; 2017.
   Google Scholar
• Mathieu E, Rainforth T, Siddharth N, et al. Disentangling disentanglement in variational autoencoders. In: International Conference on Machine Learning; PMLR; 2019. p. 4402–4412.
   Google Scholar
• Lee AX, Nagabandi A, Abbeel P, et al. Stochastic latent actor-critic: deep reinforcement learning with a latent variable model. Adv Neural Inf Process Syst. 2020;33:741–752.
   Google Scholar
• Okada M, Taniguchi T. Variational inference mpc for bayesian model-based reinforcement learning. In: Conference on Robot Learning; PMLR; 2020. p. 258–272.
   Google Scholar
• Williams RL, Lawrence DA, et al. Linear state-space control systems. John Wiley & Sons; 2007.
   Google Scholar
• Higgins I, Amos D, Pfau D, et al. Towards a definition of disentangled representations; 2018. arXiv preprint arXiv:181202230.
   Google Scholar
• Kobayashi T. q-vae for disentangled representation learning and latent dynamical systems. IEEE Robot Autom Lett. 2020;5(4):5669–5676. doi: 10.1109/LSP.2016.
   Web of Science ®Google Scholar
• Tsallis C. Possible generalization of boltzmann-gibbs statistics. J Stat Phys. 1988;52(1-2):479–487. doi: 10.1007/BF01016429
   Web of Science ®Google Scholar
• Suyari H, Tsukada M. Law of error in tsallis statistics. IEEE Trans Inf Theory. 2005;51(2):753–757. doi: 10.1109/TIT.2004.840862
   Web of Science ®Google Scholar
• Lesort T, Díaz-Rodríguez N, Goudou JF, et al. State representation learning for control: an overview. Neural Netw. 2018;108:379–392. doi: 10.1016/j.neunet.2018.07.006
   PubMed Web of Science ®Google Scholar
• Hafner D, Lillicrap T, Fischer I, et al. Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning; PMLR; 2019. p. 2555–2565.
   Google Scholar
• Kobayashi T, Murata S, Inamura T. Latent representation in human–robot interaction with explicit consideration of periodic dynamics. IEEE Trans Hum Mach Syst. 2022;52(5):928–940. doi: 10.1109/THMS.2022.3182909
   Web of Science ®Google Scholar
• Jaques M, Burke M, Hospedales TM. Newtonianvae: proportional control and goal identification from pixels via physical latent spaces. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2021. p. 4454–4463.
   Google Scholar
• Okumura R, Nishio N, Taniguchi T. Tactile-sensitive newtonianvae for high-accuracy industrial connector insertion. In: IEEE/RSJ International Conference on Intelligent Robots and Systems; IEEE; 2022. p. 4625–4631.
   Google Scholar
• Tomczak JM, Welling M. Improving variational auto-encoders using householder flow; 2016. arXiv preprint arXiv:161109630.
   Google Scholar
• Takahashi H, Iwata T, Yamanaka Y, et al. Variational autoencoder with implicit optimal priors. In: AAAI Conference on Artificial Intelligence; Vol. 33; 2019. p. 5066–5073.
   Google Scholar
• Kingma DP, Ba J. Adam: a method for stochastic optimization; 2014. arXiv preprint arXiv:14126980.
   Google Scholar
• Ilboudo WEL, Kobayashi T, Sugimoto K. Robust stochastic gradient descent with student-t distribution based first-order momentum. IEEE Trans Neural Netw Learn Syst. 2022;33(3):1324–1337. doi: 10.1109/TNNLS.2020.3041755
   PubMed Web of Science ®Google Scholar
• Takahashi H, Iwata T, Yamanaka Y, et al. Student-t variational autoencoder for robust density estimation. In: International Joint Conference on Artificial Intelligence; 2018. p. 2696–2702.
   Google Scholar
• Loaiza-Ganem G, Cunningham JP. The continuous bernoulli: fixing a pervasive error in variational autoencoders. Adv Neural Inf Process Syst. 2019;32.
   Google Scholar
• Leurent E. An environment for autonomous driving decision-making; 2018. Available from: https://github.com/eleurent/highway-env
   Google Scholar
• Paszke A, Gross S, Chintala S, et al. Automatic differentiation in pytorch. In: Advances in neural information processing systems workshop; 2017.
   Google Scholar
• Hoyer PO. Non-negative matrix factorization with sparseness constraints. J Mach Learn Res. 2004;5(9):1457–1469.
   Google Scholar
• Kemp CC, Edsinger A, Clever HM, et al. The design of stretch: a compact, lightweight mobile manipulator for indoor human environments. In: International Conference on Robotics and Automation; IEEE; 2022. p. 3150–3157.
   Google Scholar
• Kobayashi T, Enomoto T. Towards autonomous driving of personal mobility with small and noisy dataset using tsallis-statistics-based behavioral cloning; 2021. arXiv preprint arXiv:211114294.
   Google Scholar
• Aotani T, Kobayashi T, Sugimoto K. Meta-optimization of bias-variance trade-off in stochastic model learning. IEEE Access. 2021;9:148783–148799. doi: 10.1109/ACCESS.2021.3125000
   Web of Science ®Google Scholar
• Sagi O, Rokach L. Ensemble learning: a survey. Wiley Interdiscip Rev Data Min Knowl Discov. 2018;8(4):e1249. doi: 10.1002/widm.2018.8.issue-4
   Web of Science ®Google Scholar
• Graves A, Bellemare MG, Menick J, et al. Automated curriculum learning for neural networks. In: International Conference on Machine Learning; PMLR; 2017. p. 1311–1320.
   Google Scholar
• Gil M, Alajaji F, Linder T. Rényi divergence measures for commonly used univariate continuous distributions. Inf Sci (Ny). 2013;249:124–131. doi: 10.1016/j.ins.2013.06.018
   Web of Science ®Google Scholar
• Elfwing S, Uchibe E, Doya K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 2018;107:3–11. doi: 10.1016/j.neunet.2017.12.012
   PubMed Web of Science ®Google Scholar
• Ba JL, Kiros JR, Hinton GE. Layer normalization; 2016. arXiv preprint arXiv:160706450.
   Google Scholar