Related papers: SNPL: Simultaneous Policy Learning and Evaluation …

One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases. In this work, we propose a novel technique of unsupervised action planning to improve the safety of on-policy…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…

Real-world training data is often noisy; for example, human annotators assign conflicting class labels to the same instances. Partial-label learning (PLL) is a weakly supervised learning paradigm that allows training classifiers in this…

Policy robustness in Reinforcement Learning may not be desirable at any cost: the alterations caused by robustness requirements from otherwise optimal policies should be explainable, quantifiable and formally verifiable. In this work we…

Self-paced learning (SPL) is a recently raised methodology designed through simulating the learning principle of humans/animals. A variety of SPL realization schemes have been designed for different computer vision and pattern recognition…

Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we…

Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may…

Recent developments in Reinforcement learning have significantly enhanced sequential decision-making in uncertain environments. Despite their strong performance guarantees, most existing work has focused primarily on improving the…

An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas most policy search methods estimate this gradient by observing…

Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted.…

Reinforcement learning (RL) has shown great success in estimating sequential treatment strategies which take into account patient heterogeneity. However, health-outcome information, which is used as the reward for reinforcement learning…

As large language models (LLMs) are increasingly integrated into numerous applications across various domains, LLMs' safety becomes a critical concern for both application developers and intended users. Currently, great efforts have been…

Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce…

Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizing self-generated synthetic data has become crucial for…

Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL…

As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse…

Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task…

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…