Related papers: Improving Safety in Deep Reinforcement Learning us…
In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…
Although Reinforcement Learning (RL) algorithms have found tremendous success in simulated domains, they often cannot directly be applied to physical systems, especially in cases where there are hard constraints to satisfy (e.g. on safety…
Reinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. However, in many real-world RL problems, besides optimizing the main objectives, the agent is…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…
In this paper, we consider the important problem of safe exploration in reinforcement learning. While reinforcement learning is well-suited to domains with complex transition dynamics and high-dimensional state-action spaces, an additional…
Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…
Contemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types of missions they…
Unmanned autonomous vehicles (UAVs) rely on effective path planning and tracking control to accomplish complex tasks in various domains. Reinforcement Learning (RL) methods are becoming increasingly popular in control applications, as they…
We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated. We show how to exploit the typically smooth dynamics…
We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate…
Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In this family of methods, agents are trained to maximize…
Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…
This research gauges the ability of deep reinforcement learning (DRL) techniques to assist the optimization and control of fluid mechanical systems. It combines a novel, "degenerate" version of the proximal policy optimization (PPO)…
How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…
We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic manipulation tasks where good but imperfect controllers are…
Autonomous drifting is a complex and crucial maneuver for safety-critical scenarios like slippery roads and emergency collision avoidance, requiring precise motion planning and control. Traditional motion planning methods often struggle…
AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical…
Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to…
Collision-free motion is essential for mobile robots. Most approaches to collision-free and efficient navigation with wheeled robots require parameter tuning by experts to obtain good navigation behavior. This study investigates the…