TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/DQN

DQN

Deep Q-Network

Reinforcement LearningIntroduced 2000519 papers
Source Paper

Description

A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari Games case, they take in several frames of the game as an input and output state values for each action as an output.

It is usually used in conjunction with Experience Replay, for storing the episode steps in memory for off-policy learning, where samples are drawn from the replay memory at random. Additionally, the Q-Network is usually optimized towards a frozen target network that is periodically updated with the latest weights every kkk steps (where kkk is a hyperparameter). The latter makes training more stable by preventing short-term oscillations from a moving target. The former tackles autocorrelation that would occur from on-line learning, and having a replay memory makes the problem more like a supervised learning problem.

Image Source: here

Papers Using This Method

Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound2025-07-15Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study2025-07-082048: Reinforcement Learning in a Delayed Reward Environment2025-07-07VRAIL: Vectorized Reward-based Attribution for Interpretable Learning2025-06-19GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC2025-06-17Reliable Critics: Monotonic Improvement and Convergence Guarantees for Reinforcement Learning2025-06-08Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices2025-05-31Combining Deep Architectures for Information Gain estimation and Reinforcement Learning for multiagent field exploration2025-05-29The Cell Must Go On: Agar.io for Continual Reinforcement Learning2025-05-23LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models2025-05-21Automatic Reward Shaping from Confounded Offline Data2025-05-16Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs2025-05-08Interpretable Learning Dynamics in Unsupervised Reinforcement Learning2025-05-06Universal Approximation Theorem of Deep Q-Networks2025-05-04Approximation to Deep Q-Network by Stochastic Delay Differential Equations2025-05-01State-Aware IoT Scheduling Using Deep Q-Networks and Edge-Based Coordination2025-04-22AlphaGrad: Non-Linear Gradient Normalization Optimizer2025-04-22Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation2025-04-11Dynamic Operating System Scheduling Using Double DQN: A Reinforcement Learning Approach to Task Optimization2025-03-31Deep Q-Learning with Gradient Target Tracking2025-03-20