English
Related papers

Related papers: rQdia: Regularizing Q-Value Distributions With Ima…

200 papers

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the…

Machine Learning · Computer Science 2018-06-20 Will Dabney , Georg Ostrovski , David Silver , Rémi Munos

Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a…

Machine Learning · Computer Science 2022-03-17 Takuya Hiraoka , Takahisa Imagawa , Taisei Hashimoto , Takashi Onishi , Yoshimasa Tsuruoka

Image Quality Assessment (IQA) predicts perceptual quality scores consistent with human judgments. Recent RL-based IQA methods built on MLLMs focus on generating visual quality descriptions and scores, ignoring two key reliability…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Wulin Xie , Rui Dai , Ruidong Ding , Kaikui Liu , Xiangxiang Chu , Xinwen Hou , Jie Wen

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Machine Learning · Computer Science 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid action…

Machine Learning · Computer Science 2018-10-16 Jiechao Xiong , Qing Wang , Zhuoran Yang , Peng Sun , Lei Han , Yang Zheng , Haobo Fu , Tong Zhang , Ji Liu , Han Liu

We introduce the reinforcement quantum annealing (RQA) scheme in which an intelligent agent interacts with a quantum annealer that plays the stochastic environment role of learning automata and tries to iteratively find better Ising…

Quantum Physics · Physics 2020-01-03 Ramin Ayanzadeh , Milton Halem , Tim Finin

Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…

Image and Video Processing · Electrical Eng. & Systems 2025-06-23 Josué Martínez-Martínez , Olivia Brown , Mostafa Karami , Sheida Nabavi

This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of…

Computer Vision and Pattern Recognition · Computer Science 2019-12-17 Ryosuke Furuta , Naoto Inoue , Toshihiko Yamasaki

Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs). This set contains some perturbed MDPs from a nominal MDP (N-MDP) that…

Machine Learning · Computer Science 2023-11-21 Ukjo Hwang , Songnam Hong

Deep reinforcement learning continues to show tremendous potential in achieving task-level autonomy, however, its computational and energy demands remain prohibitively high. In this paper, we tackle this problem by applying quantization to…

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can…

Machine Learning · Computer Science 2015-12-10 Hado van Hasselt , Arthur Guez , David Silver

The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment…

Machine Learning · Computer Science 2016-04-25 Yitao Liang , Marlos C. Machado , Erik Talvitie , Michael Bowling

The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradigm in rate-distortion theory, an efficient regularization on…

Machine Learning · Computer Science 2017-05-02 Sohrab Ferdowsi , Slava Voloshynovskiy , Dimche Kostadinov

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Machine Learning · Computer Science 2022-05-27 Jianhan Wu , Shijing Si , Jianzong Wang , Jing Xiao

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In…

Machine Learning · Computer Science 2018-04-25 Weichao Li , Fuxian Huang , Xi Li , Gang Pan , Fei Wu

Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others…

Machine Learning · Computer Science 2019-10-21 Felipe Moreno-Vera

Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For un-experienced or less-experienced trajectories (i.e.,…

Machine Learning · Computer Science 2021-10-28 Tao Yu , Cuiling Lan , Wenjun Zeng , Mingxiao Feng , Zhizheng Zhang , Zhibo Chen

The distributional perspective on reinforcement learning (RL) has given rise to a series of successful Q-learning algorithms, resulting in state-of-the-art performance in arcade game environments. However, it has not yet been analyzed how…

Robotics · Computer Science 2020-07-03 Cristian Bodnar , Adrian Li , Karol Hausman , Peter Pastor , Mrinal Kalakrishnan

Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can…

Artificial Intelligence · Computer Science 2019-11-11 Marin Toromanoff , Emilie Wirbel , Fabien Moutarde

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

Machine Learning · Computer Science 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou