相关论文: Shielding Atari Games with Bounded Prescience

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to…

In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled…

Besides the recent impressive results on reinforcement learning (RL), safety is still one of the major research challenges in RL. RL is a machine-learning approach to determine near-optimal policies in Markov decision processes (MDPs). In…

Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the…

Deep reinforcement learning (RL) has shown promising results in the motion planning of manipulators. However, no method guarantees the safety of highly dynamic obstacles, such as humans, in RL-based manipulator control. This lack of formal…

We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…

Replacing poorly performing existing controllers with smarter solutions will decrease the energy intensity of the building sector. Recently, controllers based on Deep Reinforcement Learning (DRL) have been shown to be more effective than…

Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over…

Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player…

Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based…

Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives,…

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…

Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However, like any other software system, DRL-based software systems are susceptible to faults that pose…

In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The…

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

While Deep Reinforcement Learning (DRL) has emerged as a promising solution for intricate control tasks, the lack of explainability of the learned policies impedes its uptake in safety-critical applications, such as automated driving…

The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL) approaches under varying degrees of non-stationarity. In…

Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber…

Reinforcement learning (RL) has shown great promise in simulated environments, such as games, where failures have minimal consequences. However, the deployment of RL agents in real-world systems such as autonomous vehicles, robotics, UAVs,…

Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexity associated with the underlying deep neural networks (DNNs)…