Related papers: Curriculum Abductive Learning
Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a…
Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose Collaborative…
We propose Automatic Curricula via Expert Demonstrations (ACED), a reinforcement learning (RL) approach that combines the ideas of imitation learning and curriculum learning in order to solve challenging robotic manipulation tasks with…
Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…
Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation environments, making them brittle when deployed in real-world scenarios with more complex and uncertain conditions. Contextual MARL (cMARL) addresses…
Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is…
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method is based on progressive object-level…
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…
Active learning (AL) in open set scenarios presents a novel challenge of identifying the most valuable examples in an unlabeled data pool that comprises data from both known and unknown classes. Traditional methods prioritize selecting…
Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptimal performance across…
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…
Visual generative abductive learning studies jointly training symbol-grounded neural visual generator and inducing logic rules from data, such that after learning, the visual generation process is guided by the induced logic rules. A major…
Reinforcement Learning from Verifiable Rewards (RLVR) suffers from exploration inefficiency, where models struggle to generate successful rollouts, resulting in minimal learning signal. This challenge is particularly severe for tasks that…
Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…
In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…
Language Bottleneck Models (LBMs) are proposed to achieve interpretable image recognition by classifying images based on textual concept bottlenecks. However, current LBMs simply list all concepts together as the bottleneck layer, leading…
Machine learning has achieved much success on supervised learning tasks with large sets of well-annotated training samples. However, in many practical situations, such strong and high-quality supervision provided by training data is…
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.…
Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…