Related papers: Policy Teaching via Environment Poisoning: Trainin…
Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…
Advancements in reinforcement learning (RL) have been remarkable in recent years. However, the limitations of traditional training methods have become increasingly evident, particularly in meta-RL settings where agents face new, unseen…
Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties…
Meta reinforcement learning (meta RL), as a combination of meta-learning ideas and reinforcement learning (RL), enables the agent to adapt to different tasks using a few samples. However, this sampling-based adaptation also makes meta RL…
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…
Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is…
Reinforcement learning has seen increasing applications in real-world contexts over the past few years. However, physical environments are often imperfect and policies that perform well in simulation might not achieve the same performance…
Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In…
Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…
In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…
Reinforcement learning is one of the core components in designing an artificial intelligent system emphasizing real-time response. Reinforcement learning influences the system to take actions within an arbitrary environment either having…
Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize the stated objective in ways that may result in undesirable…
Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…
Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…
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…
This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…
The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or…
Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a…
Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…
Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…