English
Related papers

Related papers: Periodic Intra-Ensemble Knowledge Distillation for…

200 papers

Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary…

Machine Learning · Computer Science 2020-05-20 Pierre-Alexandre Kamienny , Kai Arulkumaran , Feryal Behbahani , Wendelin Boehmer , Shimon Whiteson

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to…

Machine Learning · Computer Science 2025-03-18 Amir Baghi , Jens Sjölund , Joakim Bergdahl , Linus Gisslén , Alessandro Sestini

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Efstathia Soufleri , Deepak Ravikumar , Kaushik Roy

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…

Computation and Language · Computer Science 2026-05-13 Xueqi Cheng , Xugui Zhou , Tyler Derr , Yushun Dong

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…

Machine Learning · Computer Science 2026-05-11 Giacomo Spigler

Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in…

Machine Learning · Computer Science 2022-12-08 Chao Li

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…

Machine Learning · Computer Science 2019-06-12 René Traoré , Hugo Caselles-Dupré , Timothée Lesort , Te Sun , Natalia Díaz-Rodríguez , David Filliat

Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…

Machine Learning · Computer Science 2022-03-15 Javier Maroto , Guillermo Ortiz-Jiménez , Pascal Frossard

Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to the real world in a zero-shot setting. However, a huge…

Robotics · Computer Science 2023-04-11 Yuki Kadokawa , Lingwei Zhu , Yoshihisa Tsurumine , Takamitsu Matsubara

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

Robotics · Computer Science 2023-10-16 Jinning Li , Xinyi Liu , Banghua Zhu , Jiantao Jiao , Masayoshi Tomizuka , Chen Tang , Wei Zhan

Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…

Computation and Language · Computer Science 2026-04-06 Zihe Liu , Yulong Mao , Jinan Xu , Xinrui Peng , Kaiyu Huang

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

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation…

Computation and Language · Computer Science 2021-10-05 Md Akmal Haidar , Nithin Anchuri , Mehdi Rezagholizadeh , Abbas Ghaddar , Philippe Langlais , Pascal Poupart

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with…

Computation and Language · Computer Science 2025-09-23 Minchan Kwon , Junwon Ko , Kangil Kim , Junmo Kim

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL)…

Machine Learning · Computer Science 2025-05-05 Weiqin Chen , Santiago Paternain

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Machine Learning · Computer Science 2024-04-02 Wenhao Lu , Xufeng Zhao , Thilo Fryen , Jae Hee Lee , Mengdi Li , Sven Magg , Stefan Wermter

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Ke Zhang , Jin Fan , Shaoli Huang , Yongliang Qiao , Xiaofeng Yu , Feiwei Qin

We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards…

Machine Learning · Computer Science 2025-01-08 Franco Ruggeri , Alessio Russo , Rafia Inam , Karl Henrik Johansson