Nested Mixture of Experts: Cooperative and Competitive Learning of
Hybrid Dynamical System
- URL: http://arxiv.org/abs/2011.10605v2
- Date: Thu, 29 Apr 2021 06:08:56 GMT
- Title: Nested Mixture of Experts: Cooperative and Competitive Learning of
Hybrid Dynamical System
- Authors: Junhyeok Ahn and Luis Sentis
- Abstract summary: We propose a nested mixture of experts (NMOE) for representing and learning hybrid dynamical systems.
An NMOE combines both white-box and black-box models while optimizing bias-variance trade-off.
An NMOE provides a structured method for incorporating various types of prior knowledge by training the associative experts cooperatively or competitively.
- Score: 2.055949720959582
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Model-based reinforcement learning (MBRL) algorithms can attain significant
sample efficiency but require an appropriate network structure to represent
system dynamics. Current approaches include white-box modeling using analytic
parameterizations and black-box modeling using deep neural networks. However,
both can suffer from a bias-variance trade-off in the learning process, and
neither provides a structured method for injecting domain knowledge into the
network. As an alternative, gray-box modeling leverages prior knowledge in
neural network training but only for simple systems. In this paper, we devise a
nested mixture of experts (NMOE) for representing and learning hybrid dynamical
systems. An NMOE combines both white-box and black-box models while optimizing
bias-variance trade-off. Moreover, an NMOE provides a structured method for
incorporating various types of prior knowledge by training the associative
experts cooperatively or competitively. The prior knowledge includes
information on robots' physical contacts with the environments as well as their
kinematic and dynamic properties. In this paper, we demonstrate how to
incorporate prior knowledge into our NMOE in various continuous control
domains, including hybrid dynamical systems. We also show the effectiveness of
our method in terms of data-efficiency, generalization to unseen data, and
bias-variance trade-off. Finally, we evaluate our NMOE using an MBRL setup,
where the model is integrated with a model-based controller and trained online.
Related papers
- Joint torques prediction of a robotic arm using neural networks [4.019105975232108]
Traditional approaches to deriving dynamic models are based on the application of Lagrangian or Newtonian mechanics.
A popular alternative is the application of Machine Learning (ML) techniques in the context of a "black-box" methodology.
This paper reports on our experience with this approach for a real-life 6 degrees of freedom (DoF) manipulator.
arXiv Detail & Related papers (2024-03-28T09:38:26Z) - BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion [56.9358325168226]
We propose a Bagging deep learning training algorithm based on Efficient Neural network Diffusion (BEND)
Our approach is simple but effective, first using multiple trained model weights and biases as inputs to train autoencoder and latent diffusion model.
Our proposed BEND algorithm can consistently outperform the mean and median accuracies of both the original trained model and the diffused model.
arXiv Detail & Related papers (2024-03-23T08:40:38Z) - Demolition and Reinforcement of Memories in Spin-Glass-like Neural
Networks [0.0]
The aim of this thesis is to understand the effectiveness of Unlearning in both associative memory models and generative models.
The selection of structured data enables an associative memory model to retrieve concepts as attractors of a neural dynamics with considerable basins of attraction.
A novel regularization technique for Boltzmann Machines is presented, proving to outperform previously developed methods in learning hidden probability distributions from data-sets.
arXiv Detail & Related papers (2024-03-04T23:12:42Z) - How neural networks learn to classify chaotic time series [77.34726150561087]
We study the inner workings of neural networks trained to classify regular-versus-chaotic time series.
We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
arXiv Detail & Related papers (2023-06-04T08:53:27Z) - Dynamic Mixed Membership Stochastic Block Model for Weighted Labeled
Networks [3.5450828190071655]
A new family of Mixed Membership Block Models (MMSBM) allows to model static labeled networks under the assumption of mixed-membership clustering.
We show that our method significantly differs from existing approaches, and allows to model more complex systems --dynamic labeled networks.
arXiv Detail & Related papers (2023-04-12T15:01:03Z) - ConCerNet: A Contrastive Learning Based Framework for Automated
Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling.
We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
arXiv Detail & Related papers (2023-02-11T21:07:30Z) - Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems.
Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC.
We provide a practical parametrization of the core optimization problem.
arXiv Detail & Related papers (2021-07-08T18:01:02Z) - Using Data Assimilation to Train a Hybrid Forecast System that Combines
Machine-Learning and Knowledge-Based Components [52.77024349608834]
We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements.
We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
arXiv Detail & Related papers (2021-02-15T19:56:48Z) - Model-Based Deep Learning [155.063817656602]
Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques.
Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance.
We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
arXiv Detail & Related papers (2020-12-15T16:29:49Z) - Distributed Training of Deep Learning Models: A Taxonomic Perspective [11.924058430461216]
Distributed deep learning systems (DDLS) train deep neural network models by utilizing the distributed resources of a cluster.
We aim to shine some light on the fundamental principles that are at work when training deep neural networks in a cluster of independent machines.
arXiv Detail & Related papers (2020-07-08T08:56:58Z) - Learning Queuing Networks by Recurrent Neural Networks [0.0]
We propose a machine-learning approach to derive performance models from data.
We exploit a deterministic approximation of their average dynamics in terms of a compact system of ordinary differential equations.
This allows for an interpretable structure of the neural network, which can be trained from system measurements to yield a white-box parameterized model.
arXiv Detail & Related papers (2020-02-25T10:56:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.