Related papers: Uncertainty-Aware Policy Optimization: A Robust, A…
Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…
In recent years, there has been significant progress in applying deep reinforcement learning (RL) for solving challenging problems across a wide variety of domains. Nevertheless, convergence of various methods has been shown to suffer from…
Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from…
In many contemporary applications such as healthcare, finance, robotics, and recommendation systems, continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We consider a…
In this paper, we develop a two-stage data-driven approach to address the adjustable robust optimization problem, where the uncertainty set is adjustable to manage infeasibility caused by significant or poorly quantified uncertainties. In…
Deep reinforcement learning is an increasingly popular technique for synthesising policies to control an agent's interaction with its environment. There is also growing interest in formally verifying that such policies are correct and…
Optimal sensor placement enhances the efficiency of a variety of applications for monitoring dynamical systems. It has been established that deterministic solutions to the sensor placement problem are insufficient due to the many…
Robust optimization methods have shown practical advantages in a wide range of decision-making applications under uncertainty. Recently, their efficacy has been extended to multi-period settings. Current approaches model uncertainty either…
Reinforcement Learning has applications in field of mechatronics, robotics, and other resource-constrained control system. Problem of resource allocation is primarily solved using traditional predefined techniques and modern deep learning…
Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…
Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout…
Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While there has been…
Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently…
Deep reinforcement learning (DRL) has emerged as a promising approach for developing more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a neural network-based driving policy. However, the black-box…
There is growing importance to detecting faults and implementing the best methods in industrial and real-world systems. We are searching for the most trustworthy and practical data-based fault detection methods proposed by artificial…
We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable. Standard techniques for uncertainty estimation, however, come along with specific combinations of strengths and weaknesses, e.g., with respect to…
This paper proposes a robust control design method using reinforcement-learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement-learning algorithm with a new…
Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…
While deep reinforcement learning (RL) agents have showcased strong results across many domains, a major concern is their inherent opaqueness and the safety of such systems in real-world use cases. To overcome these issues, we need agents…