相关论文: Oracle-Guided Soft Shielding for Safe Move Predict…

Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this paper, we propose a principled algorithm for safe exploration…

Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form…

In this paper, we propose a method to develop trustworthy reinforcement learning systems. To ensure safety especially during exploration, we automatically synthesize a correct-by-construction runtime enforcer, called a shield, that blocks…

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…

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, facilitates a better understanding of an agent's decisions. We tackle this problem in the options…

In the last decade, reinforcement learning successfully solved complex control tasks and decision-making problems, like the Go board game. Yet, there are few success stories when it comes to deploying those algorithms to real-world…

Reinforcement learning (RL) has been successfully applied to a variety of robotics applications, where it outperforms classical methods. However, the safety aspect of RL and the transfer to the real world remain an open challenge. A…

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

An inherent problem of reinforcement learning is performing exploration of an environment through random actions, of which a large portion can be unproductive. Instead, exploration can be improved by initializing the learning policy with an…

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing suboptimal yet conservative…

Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinforcement learning and achieve hard safety guarantees. However, existing safety…

In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide guarantees on the (1) performance and (2) safety of the resulting policy. A technique called…

In many real recommender systems, novel items are added frequently over time. The importance of sufficiently presenting novel actions has widely been acknowledged for improving long-term user engagement. A recent work builds on Off-Policy…

This work addresses the problem of offline safe imitation learning (IL), where the goal is to learn safe and reward-maximizing policies from demonstrations that do not have per-timestep safety cost or reward information. In many real-world…

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

In this paper, we study oracle-efficient algorithms for beyond worst-case analysis of online learning. We focus on two settings. First, the smoothed analysis setting of [RST11,HRS22] where an adversary is constrained to generating samples…

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-inefficient and maximising…