ﻻ يوجد ملخص باللغة العربية
We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample-based version of PILCO with neural network dynamics (Deep-PILCO). We propose training a neural network dynamics model using variational dropout with truncated Log-Normal noise. This allows us to obtain a dynamics model with calibrated uncertainty, which can be used to simulate controller executions via rollouts. We also describe set of techniques, inspired by viewing PILCO as a recurrent neural network model, that are crucial to improve the convergence of the method. We test our method on a variety of benchmark tasks, demonstrating data-efficiency that is competitive with PILCO, while being able to optimize complex neural network controllers. Finally, we assess the performance of the algorithm for learning motor controllers for a six legged autonomous underwater vehicle. This demonstrates the potential of the algorithm for scaling up the dimensionality and dataset sizes, in more complex control tasks.
We provide a novel approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions,
Transporting suspended payloads is challenging for autonomous aerial vehicles because the payload can cause significant and unpredictable changes to the robots dynamics. These changes can lead to suboptimal flight performance or even catastrophic fai
Natural beings undergo a morphological development process of their bodies while they are learning and adapting to the environments they face from infancy to adulthood. In fact, this is the period where the most important learning pro-cesses, those t
Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We present a
Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, however, makes their output difficult to verify and predict, which limits th