Related papers: SNPL: Simultaneous Policy Learning and Evaluation …
Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the…
Learning control policies for complex, long-horizon tasks is a central challenge in robotics and autonomous systems. Signal Temporal Logic (STL) offers a powerful and expressive language for specifying such tasks, but its non-Markovian…
Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these…
Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…
State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent drawback of this strategy stems from the quality of the…
Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric…
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…
Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical…
Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…
Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…
Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…
The number and dynamic nature of web and mobile applications presents significant challenges for assessing their compliance with data protection laws. In this context, symbolic and statistical Natural Language Processing (NLP) techniques…
Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…
Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…
Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…
Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from…
Semi-supervised continual learning (SSCL) seeks to leverage both labeled and unlabeled data in a sequential learning setup, aiming to reduce annotation costs while managing continual data arrival. SSCL introduces complex challenges,…
Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g.,…
The unaffordable computation load of nonlinear model predictive control (NMPC) has prevented it for being used in robots with high sampling rates for decades. This paper is concerned with the policy learning problem for nonlinear MPC with…