English
Related papers

Related papers: Policy Distillation

200 papers

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

We study policy distillation under privileged information, where a student policy with only partial observations must learn from a teacher with full-state access. A key challenge is information asymmetry: the student cannot directly access…

Robotics · Computer Science 2025-05-15 Yujin Kim , Nathaniel Chin , Arnav Vasudev , Sanjiban Choudhury

A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind's team called the approach:…

Machine Learning · Computer Science 2015-12-08 Ivan Sorokin , Alexey Seleznev , Mikhail Pavlov , Aleksandr Fedorov , Anastasiia Ignateva

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

Real world deployment of multi agent reinforcement learning MARL systems is fundamentally constrained by limited compute memory and inference time. While expert policies achieve high performance they rely on costly decision cycles and large…

Artificial Intelligence · Computer Science 2026-04-09 Monirul Islam Pavel , Siyi Hu , Muhammad Anwar Masum , Mahardhika Pratama , Ryszard Kowalczyk , Zehong Jimmy Cao

Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures between the teacher and student network. In…

Machine Learning · Computer Science 2020-11-24 Jonathan Raiman

While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a…

Artificial Intelligence · Computer Science 2026-05-26 Yinyi Luo , Yiqiao Jin , Weichen Yu , Mengqi Zhang , Srijan Kumar , Xiaoxiao Li , Weijie Xu , Xin Chen , Jindong Wang

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would…

Artificial Intelligence · Computer Science 2018-09-07 Jack Harmer , Linus Gisslén , Jorge del Val , Henrik Holst , Joakim Bergdahl , Tom Olsson , Kristoffer Sjöö , Magnus Nordin

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…

Computation and Language · Computer Science 2019-04-23 Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao

The deep reinforcement learning method usually requires a large number of training images and executing actions to obtain sufficient results. When it is extended a real-task in the real environment with an actual robot, the method will be…

Computer Vision and Pattern Recognition · Computer Science 2018-06-05 Daiki Kimura

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new…

Machine Learning · Computer Science 2017-07-25 Tuomas Haarnoja , Haoran Tang , Pieter Abbeel , Sergey Levine

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

Vision-Language-Action Models (VLAs) have demonstrated remarkable generalization capabilities in real-world experiments. However, their success rates are often not on par with expert policies, and they require fine-tuning when the setup…

Robotics · Computer Science 2025-08-05 Tobias Jülg , Wolfram Burgard , Florian Walter

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…

Machine Learning · Computer Science 2021-07-05 Anssi Kanervisto , Christian Scheller , Yanick Schraner , Ville Hautamäki

Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical.…

Machine Learning · Computer Science 2026-03-31 Yuri Kinoshita , Naoki Nishikawa , Taro Toyoizumi

One of the long-standing challenges in Artificial Intelligence for learning goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential problems has…

Neural and Evolutionary Computing · Computer Science 2017-05-23 Sahil Sharma , Ashutosh Jha , Parikshit Hegde , Balaraman Ravindran

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning,…

Machine Learning · Computer Science 2013-12-20 Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Alex Graves , Ioannis Antonoglou , Daan Wierstra , Martin Riedmiller

We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained…

Machine Learning · Computer Science 2015-10-16 Hao Yi Ong , Kevin Chavez , Augustus Hong