Deep Attention Recurrent Q-Network

2015-12-05 · Ivan Sorokin, Alexey Seleznev, Mikhail Pavlov, Aleksandr Fedorov, Anastasiia Ignateva

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: Deep Q-Network (DQN). We present an extension of DQN by "soft" and "hard" attention mechanisms. Tests of the proposed Deep Attention Recurrent Q-Network (DARQN) algorithm on multiple Atari 2600 games show level of performance superior to that of DQN. Moreover, built-in attention mechanisms allow a direct online monitoring of the training process by highlighting the regions of the game screen the agent is focusing on when making decisions.

📄 PDF Abstract BibTeX arXiv:1512.01693

Code (3)

5vision/DARQN 공식 구현

ulstu/ml

ulstu/robotics_ml

Tasks

Atari GamesDeep AttentionHard Attentionreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Channel Recurrent Attention Networks for Video Pedestrian Retrieval

2020-10-07 · Pengfei Fang, Pan Ji, Jieming Zhou, Lars Petersson 외

Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks. In this work, we propose a fully attentional network, termed …

Person Retrieval Retrieval

Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks

2025-07-25 · Kai Liu, Zhan Su, Peijie Dong, Fengran Mo 외 arxiv

Recently, recurrent large language models (Recurrent LLMs) with linear computational complexity have re-emerged as efficient alternatives to self-attention-based LLMs (Self-Attention LLMs), which have quadratic complexit…

A recurrent vision transformer shows signatures of primate visual attention

2025-02-16 · Jonathan Morgan, Badr Albanna, James P. Herman

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that…

Change Detection

Dual Recurrent Attention Units for Visual Question Answering

2018-02-01 · Ahmed Osman, Wojciech Samek

Visual Question Answering (VQA) requires AI models to comprehend data in two domains, vision and text. Current state-of-the-art models use learned attention mechanisms to extract relevant information from the input domai…

Question Answering Visual Question Answering Visual Question Answering (VQA)

Unifying Top-down and Bottom-up for Recurrent Visual Attention

2021-09-29 · Gang Chen

The idea of using the recurrent neural network for visual attention has gained popularity in computer vision community. Although the recurrent visual attention model (RAM) leverages the glimpses with more large patch siz…

Q-Learning