mlsanityData to 14 Oct 2026

Deep Attention Recurrent Q-Network

arXiv 1512.01693 ↗First posted 5 Dec 2015cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 9; 2023: 5; 2024: 2; 2025: 5.

27 papers.

Sort:

By area:

  1. 2022Deep Transformer Q-Networks for Partially Observable Reinforcement Learningcited by 36
  2. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  3. 2021Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Modelcited by 16
  4. 2023FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learningcited by 13
  5. 2021Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learningcited by 9
  6. 2022Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Taskscited by 9
  7. 2022Attention Option-Criticcited by 8
  8. 2021Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learningcited by 6
  9. 2022Transformer in Transformer as Backbone for Deep Reinforcement Learningcited by 6
  10. 2022On learning history based policies for controlling Markov decision processescited by 5
  11. 2023Approximate information state based convergence analysis of recurrent Q-learningcited by 5
  12. 2024Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluationcited by 5
15 more
  1. 2022Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformerscited by 4
  2. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  3. 2022Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Drivingcited by 3
  4. 2021Pretrained Encoders are All You Needcited by 2
  5. 2022Deep Reinforcement Learning with Swin Transformerscited by 2
  6. 2023Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correctioncited by 2
  7. 2025Socially aware navigation for mobile robots: a survey on deep reinforcement learning approachescited by 2
  8. 2025Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolutioncited by 1
  9. 2021Neural Networks and Denotationcited by 0
  10. 2023Active Vision Reinforcement Learning under Limited Visual Observabilitycited by 0
  11. 2023RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learningcited by 0
  12. 2024Portfolio Management using Deep Reinforcement Learningcited by 0
  13. 2025Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learningcited by 0
  14. 2025Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processescited by 0
  15. 2025Optimizing Sensory Neurons: Nonlinear Attention Mechanisms for Accelerated Convergence in Permutation-Invariant Neural Networks for Reinforcement Learningcited by 0