English
Related papers

Related papers: In-context Reinforcement Learning with Algorithm D…

200 papers

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates…

Computation and Language · Computer Science 2024-03-19 Kevin Yang , Dan Klein , Asli Celikyilmaz , Nanyun Peng , Yuandong Tian

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

Machine Learning · Computer Science 2026-03-23 Siyan Zhao , Zhihui Xie , Mengchen Liu , Jing Huang , Guan Pang , Feiyu Chen , Aditya Grover

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Computation and Language · Computer Science 2020-10-30 Alexander Lin , Jeremy Wohlwend , Howard Chen , Tao Lei

Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in…

Machine Learning · Computer Science 2020-10-27 Hossein Mobahi , Mehrdad Farajtabar , Peter L. Bartlett

Learning a good state representation is a critical skill when dealing with multiple tasks in Reinforcement Learning as it allows for transfer and better generalization between tasks. However, defining what constitute a useful representation…

Machine Learning · Computer Science 2022-10-06 Valentin Guillet , Dennis G. Wilson , Carlos Aguilar-Melchor , Emmanuel Rachelson

Reinforcement learning (RL) has played an important role in improving the reasoning ability of large language models (LLMs). Some studies apply RL directly to \textit{smaller} base models (known as zero-RL) and also achieve notable…

Artificial Intelligence · Computer Science 2025-05-28 Xiao Hu , Xingyu Lu , Liyuan Mao , YiFan Zhang , Tianke Zhang , Bin Wen , Fan Yang , Tingting Gao , Guorui Zhou

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Neural and Evolutionary Computing · Computer Science 2019-12-04 J. Gomez Robles , J. Vanschoren

Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Umberto Cappellazzo , Daniele Falavigna , Alessio Brutti

Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target…

Machine Learning · Computer Science 2026-05-20 Thien Le , Melanie Weber

The emerging task of fine-grained image classification in low-data regimes assumes the presence of low inter-class variance and large intra-class variation along with a highly limited amount of training samples per class. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Dmitry Demidov , Abduragim Shtanchaev , Mihail Mihaylov , Mohammad Almansoori

Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial…

Cryptography and Security · Computer Science 2016-03-15 Nicolas Papernot , Patrick McDaniel , Xi Wu , Somesh Jha , Ananthram Swami

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

Machine Learning · Computer Science 2026-02-04 Mahyar Alinejad , Yue Wang , George Atia

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Machine Learning · Computer Science 2025-10-06 Yuda Song , Dhruv Rohatgi , Aarti Singh , J. Andrew Bagnell

Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this…

Machine Learning · Computer Science 2024-11-19 Feng Chen , Fuguang Han , Cong Guan , Lei Yuan , Zhilong Zhang , Yang Yu , Zongzhang Zhang

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to…

Robotics · Computer Science 2026-05-29 Victor Kowalski , Chengxi Li , Dongheui Lee

Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily…

Computation and Language · Computer Science 2024-07-26 Joe Stacey , Marek Rei

Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the…

Machine Learning · Computer Science 2020-02-04 Zhang-Wei Hong , Prabhat Nagarajan , Guilherme Maeda

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration…

Machine Learning · Computer Science 2024-06-07 Qingyuan Wu , Simon Sinong Zhan , Yixuan Wang , Yuhui Wang , Chung-Wei Lin , Chen Lv , Qi Zhu , Jürgen Schmidhuber , Chao Huang

Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be summarized as a min-max optimization process, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yuzheng Wang , Zhaoyu Chen , Dingkang Yang , Yuanhang Wang , Lizhe Qi