Related papers: CROP: Certifying Robust Policies for Reinforcement…
Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL…
Establishing stability certificates for closed-loop systems under reinforcement learning (RL) policies is essential to move beyond empirical performance and offer guarantees of system behavior. Classical Lyapunov methods require a strict…
Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially…
Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…
In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…
Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…
Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two…
Neural Lyapunov and barrier certificates have recently been used as powerful tools for verifying the safety and stability properties of deep reinforcement learning (RL) controllers. However, existing methods offer guarantees only under…
Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep learning. However, for some classification problems, local…
Recent breakthroughs both in reinforcement learning and trajectory optimization have made significant advances towards real world robotic system deployment. Reinforcement learning (RL) can be applied to many problems without needing any…
To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which…
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…
Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization…
Over the past few years, the acceleration of computing resources and research in deep learning has led to significant practical successes in a range of tasks, including in particular in computer vision. Building on these advances,…
Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…
Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass…
In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on…
Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…
In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To encourage constraint satisfaction, existing RL algorithms typically rely on Constrained Markov Decision Processes and discourage constraint…
Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making under uncertainty. Given the impact both fields have had independently across numerous domains, there is…