A review of safe reinforcement learning: Methods, theory and applications
Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …
making tasks. However, safety concerns are raised during deploying RL in real-world …
A review of safe reinforcement learning: Methods, theories and applications
Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …
making tasks. However, safety concerns are raised during deploying RL in real-world …
Multi-task learning as a bargaining game
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for
several tasks. Joint training reduces computation costs and improves data efficiency; …
several tasks. Joint training reduces computation costs and improves data efficiency; …
On the almost sure convergence of stochastic gradient descent in non-convex problems
In this paper, we analyze the trajectories of stochastic gradient descent (SGD) with the aim of
understanding their convergence properties in non-convex problems. We first show that the …
understanding their convergence properties in non-convex problems. We first show that the …
AdaGrad avoids saddle points
Adaptive first-order methods in optimization have widespread ML applications due to their
ability to adapt to non-convex landscapes. However, their convergence guarantees are …
ability to adapt to non-convex landscapes. However, their convergence guarantees are …
Gradient-descent quantum process tomography by learning Kraus operators
We perform quantum process tomography (QPT) for both discrete-and continuous-variable
quantum systems by learning a process representation using Kraus operators. The Kraus …
quantum systems by learning a process representation using Kraus operators. The Kraus …
Riemannian stochastic optimization methods avoid strict saddle points
Many modern machine learning applications-from online principal component analysis to
covariance matrix identification and dictionary learning-can be formulated as minimization …
covariance matrix identification and dictionary learning-can be formulated as minimization …
Robust reinforcement learning via adversarial training with langevin dynamics
We introduce a\emph {sampling} perspective to tackle the challenging task of training robust
Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin …
Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin …
Evaluating model-free reinforcement learning toward safety-critical tasks
Safety comes first in many real-world applications involving autonomous agents. Despite a
large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there …
large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there …
Mathematical introduction to deep learning: methods, implementations, and theory
This book aims to provide an introduction to the topic of deep learning algorithms. We review
essential components of deep learning algorithms in full mathematical detail including …
essential components of deep learning algorithms in full mathematical detail including …