相关论文: Emergent Complexity and Zero-shot Transfer via Uns…

Self-driving software pipelines include components that are learned from a significant number of training examples, yet it remains challenging to evaluate the overall system's safety and generalization performance. Together with scaling up…

The ability to transfer in reinforcement learning is key towards building an agent of general artificial intelligence. In this paper, we consider the problem of learning to simultaneously transfer across both environments (ENV) and tasks…

Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must…

The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As noise levels increase, the outputs of the trained model exhibit…

We present a new approach ARLPCG: Adversarial Reinforcement Learning for Procedural Content Generation, which procedurally generates and tests previously unseen environments with an auxiliary input as a control variable. Training RL agents…

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…

Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI…

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…

Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track…

Reinforcement learning (RL) has been demonstrated suitable to develop agents that play complex games with human-level performance. However, it is not understood how to effectively use RL to perform cybersecurity tasks. To develop such…

Designing a perfect reward function that depicts all the aspects of the intended behavior is almost impossible, especially generalizing it outside of the training environments. Active Inverse Reward Design (AIRD) proposed the use of a…

We study a Stackelberg game between one attacker and one defender in a configurable environment. The defender picks a specific environment configuration. The attacker observes the configuration and attacks via Reinforcement Learning (RL…

Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often…

State of the art reinforcement learning has enabled training agents on tasks of ever increasing complexity. However, the current paradigm tends to favor training agents from scratch on every new task or on collections of tasks with a view…

Transferring knowledge across domains is one of the most fundamental problems in machine learning, but doing so effectively in the context of reinforcement learning remains largely an open problem. Current methods make strong assumptions on…

In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…