Related papers: PROWL: Prioritized Regret-Driven Optimization for …
Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a…
A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard…
We study online learning problems in which the learner has extra knowledge about the adversary's behaviour, i.e., in game-theoretic settings where opponents typically follow some no-external regret learning algorithms. Under this…
Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving. However, despite their advanced capabilities, DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in…
We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL…
Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…
Deep learning models have become increasingly large and complex, resulting in higher memory consumption and computational demands. Consequently, model loading times and initial inference latency have increased, posing significant challenges…
Constrained Reinforcement Learning (CRL) aims to optimize decision-making policies under constraint conditions, making it highly applicable to safety-critical domains such as autonomous driving, robotics, and power grid management. However,…
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust…
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,…
A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…
Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…
Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem…
World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune…
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…
Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…
Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…
Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the…
Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation encourages transfer…