Agile DQN: adaptive deep recurrent attention reinforcement learning for autonomous UAV obstacle a...

Agile DQN: adaptive deep recurrent attention reinforcement learning for autonomous UAV obstacle avoidance  Nature

AI Startup Morphic to Produce Anime Series ‘Dqn,’ Launches $1 Million Creator Fund for Emerging F...

AI Startup Morphic to Produce Anime Series ‘Dqn,’ Launches $1 Million Creator Fund for Emerging Filmmakers (Exclusive)  IMDb

Morphic Launches AI Anime ‘DQN’ & $1 Million AI Filmmaker Fund - Animation Magazine

Morphic Launches AI Anime ‘DQN’ & $1 Million AI Filmmaker Fund  Animation Magazine

(PDF) Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avo...

(PDF) Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance  researchgate.net

DESIGN A PATH – PLANNING STRATEGY FOR MOBILE ROBOT IN MULTI-STRUCTURED ENVIRONMENT BASED ON DISTR...

DESIGN A PATH – PLANNING STRATEGY FOR MOBILE ROBOT IN MULTI-STRUCTURED ENVIRONMENT BASED ON DISTRIBUTIONAL REINFORCEMENT LEARNING  ScienceDirect.com

Morphic to Produce AI Anime Series, Launches $1 Million Creator Fund - Variety

Morphic to Produce AI Anime Series, Launches $1 Million Creator Fund  Variety

Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance...

Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance  Nature

Morphic Launches Trailer For DQN - Bubbleblabber

Morphic Launches Trailer For DQN  Bubbleblabber

Which RL Algorithm Actually Works? I Put 8 to the Test on CartPole | by Thomas Reinecke | Jul, 20...

Which RL Algorithm Actually Works? I Put 8 to the Test on CartPole | by Thomas Reinecke | Jul, 2025  DataDrivenInvestor

Noisy Dueling Double Deep Q-Network algorithm for autonomous underwater vehicle path planning - F...

Noisy Dueling Double Deep Q-Network algorithm for autonomous underwater vehicle path planning  Frontiers

Deep Q Networks (DQN) and Dueling DQN. - researchgate.net

Deep Q Networks (DQN) and Dueling DQN.  researchgate.net

Multi objective reinforcement learning driven task offloading algorithm for satellite edge comput...

Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks  Nature

The structure of the PSO-DQN algorithm. We combine the DQN framework... - researchgate.net

The structure of the PSO-DQN algorithm. We combine the DQN framework...  researchgate.net

Enhanced Q learning and deep reinforcement learning for unmanned combat intelligence planning in ...

Enhanced Q learning and deep reinforcement learning for unmanned combat intelligence planning in adversarial environments  Nature

Fig. 5. In RL, the DQN and DDPG architectures accept same state... - researchgate.net

Fig. 5. In RL, the DQN and DDPG architectures accept same state...  researchgate.net

An integrating RAG-LLM and deep Q-network framework for intelligent fish control systems - Nature

An integrating RAG-LLM and deep Q-network framework for intelligent fish control systems  Nature

Dynamic appliance scheduling and energy management in smart homes using adaptive reinforcement le...

Dynamic appliance scheduling and energy management in smart homes using adaptive reinforcement learning techniques  Nature

Estimating best nanomaterial for energy harvesting through reinforcement learning DQN coupled wit...

Estimating best nanomaterial for energy harvesting through reinforcement learning DQN coupled with fuzzy PROMETHEE under road-based conditions  Nature

Comparative analysis of Q-learning, SARSA, and deep Q-network for microgrid energy management - N...

Comparative analysis of Q-learning, SARSA, and deep Q-network for microgrid energy management  Nature

The analysis of deep reinforcement learning for dynamic graphical games under artificial intellig...

The analysis of deep reinforcement learning for dynamic graphical games under artificial intelligence  Nature

Improving traffic light systems using Deep Q-networks - ScienceDirect.com

Improving traffic light systems using Deep Q-networks  ScienceDirect.com

Dyna-PINN: Physics-informed deep dyna-q reinforcement learning for intelligent control of buildin...

Dyna-PINN: Physics-informed deep dyna-q reinforcement learning for intelligent control of building heating system in low-diversity training data regimes  ScienceDirect.com

Figure 5. Key performance metrics for Deep Q-Networks(DQN) - researchgate.net

Figure 5. Key performance metrics for Deep Q-Networks(DQN)  researchgate.net

Figure 3. Illustration of the Deep Q Network (DQN) based RL approach... - researchgate.net

Figure 3. Illustration of the Deep Q Network (DQN) based RL approach...  researchgate.net

LCA: Deep Reinforcement Learning-Based Congestion Avoidance Routing Model in SDN - ScienceDirect.com

LCA: Deep Reinforcement Learning-Based Congestion Avoidance Routing Model in SDN  ScienceDirect.com

Collision-free motion-constrained path planning for multiple Unmanned Delivery Vehicles based on ...

Collision-free motion-constrained path planning for multiple Unmanned Delivery Vehicles based on heuristic deep reinforcement learning  ScienceDirect.com

Fig. 1. Interaction between an environment and two agents: DQN and BDRL - researchgate.net

Fig. 1. Interaction between an environment and two agents: DQN and BDRL  researchgate.net

A reinforcement learning approach for reducing traffic congestion using deep Q learning - Nature

A reinforcement learning approach for reducing traffic congestion using deep Q learning  Nature

Demystifying Policy Optimization in RL: An Introduction to PPO and GRPO - Towards Data Science

Demystifying Policy Optimization in RL: An Introduction to PPO and GRPO  Towards Data Science

Neural network compression for reinforcement learning tasks - Scientific Reports - Nature

Neural network compression for reinforcement learning tasks - Scientific Reports  Nature

Human-level control through deep reinforcement learning - Nature

Human-level control through deep reinforcement learning  Nature

Application of artificial intelligence based on state grid ESG platform in clean energy schedulin...

Application of artificial intelligence based on state grid ESG platform in clean energy scheduling optimization  Nature

Deep reinforcement learning model for Multi-Ship collision avoidance decision making design imple...

Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis  Nature

Rainbow: The Colorful Evolution of Deep Q-Networks - Towards Data Science

Rainbow: The Colorful Evolution of Deep Q-Networks  Towards Data Science

A timeline of major milestones and breakthroughs in reinforcement... - researchgate.net

A timeline of major milestones and breakthroughs in reinforcement...  researchgate.net

Visualizing Turtlebot3 Burger’s movement actions for environment interaction. - researchgate.net

Visualizing Turtlebot3 Burger’s movement actions for environment interaction.  researchgate.net

Makespan Optimisation in Cloudlet Scheduling with Improved DQN Algorithm in Cloud Computing - Wil...

Makespan Optimisation in Cloudlet Scheduling with Improved DQN Algorithm in Cloud Computing  Wiley Online Library

Deep Q-Network (DQN)-II - Towards Data Science

Deep Q-Network (DQN)-II  Towards Data Science

Rainbow DQN – The Best Reinforcement Learning Has to Offer? - Towards Data Science

Rainbow DQN – The Best Reinforcement Learning Has to Offer?  Towards Data Science

OpenAI Baselines: DQN - OpenAI

OpenAI Baselines: DQN  OpenAI

Global path planning algorithm based on double DQN for multi-tasks amphibious unmanned surface ve...

Global path planning algorithm based on double DQN for multi-tasks amphibious unmanned surface vehicle  ScienceDirect.com

Multi-level deep Q-networks for Bitcoin trading strategies - Nature

Multi-level deep Q-networks for Bitcoin trading strategies  Nature

(PDF) Improved DQN Algorithm for Path Planning of Autonomous Mobile Robots - researchgate.net

(PDF) Improved DQN Algorithm for Path Planning of Autonomous Mobile Robots  researchgate.net

Deep Q-Networks: theory and implementation - Towards Data Science

Deep Q-Networks: theory and implementation  Towards Data Science

Deep Q-Network (DQN)-I - Towards Data Science

Deep Q-Network (DQN)-I  Towards Data Science

Deep Reinforcement Learning - Google DeepMind

Deep Reinforcement Learning  Google DeepMind

RRT-guided experience generation for reinforcement learning in autonomous lane keeping - Nature

RRT-guided experience generation for reinforcement learning in autonomous lane keeping  Nature

Active equalization control method for battery pack based on Double-DQN - ScienceDirect.com

Active equalization control method for battery pack based on Double-DQN  ScienceDirect.com

An Optimistic Perspective on Offline Reinforcement Learning - Google Research

An Optimistic Perspective on Offline Reinforcement Learning  Google Research

Research on the multi-timescale optimal voltage control method for distribution network based on ...

Research on the multi-timescale optimal voltage control method for distribution network based on a DQN-DDPG algorithm  Frontiers

Applied Reinforcement Learning III: Deep Q-Networks (DQN) - Towards Data Science

Applied Reinforcement Learning III: Deep Q-Networks (DQN)  Towards Data Science

Fig. 4 Difference between Q-Learning and DQN - researchgate.net

Fig. 4 Difference between Q-Learning and DQN  researchgate.net

Beat Atari with Deep Reinforcement Learning! (Part 1: DQN) - Becoming Human: Artificial Intellige...

Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)  Becoming Human: Artificial Intelligence Magazine

Practical Guide to DQN - Towards Data Science

Practical Guide to DQN  Towards Data Science

Dynamic scheduling for flexible job shop based on MachineRank algorithm and reinforcement learnin...

Dynamic scheduling for flexible job shop based on MachineRank algorithm and reinforcement learning  Nature

Improving the interpretability of deep reinforcement learning in urban drainage system operation ...

Improving the interpretability of deep reinforcement learning in urban drainage system operation  ScienceDirect.com

Figure 7: Comparison of Polyak averaging constants (a) and Single DQN... - researchgate.net

Figure 7: Comparison of Polyak averaging constants (a) and Single DQN...  researchgate.net

FIGURE 6. DQN architecture has a main network, a target network, and a... - researchgate.net

FIGURE 6. DQN architecture has a main network, a target network, and a...  researchgate.net

Fig. 7: Convergence of the PPO algorithm compared to the DQN algorithm - researchgate.net

Fig. 7: Convergence of the PPO algorithm compared to the DQN algorithm  researchgate.net

Beat Atari with Deep Reinforcement Learning! (Part 2: DQN improvements) - Becoming Human: Artific...

Beat Atari with Deep Reinforcement Learning! (Part 2: DQN improvements)  Becoming Human: Artificial Intelligence Magazine

A Gentle Introduction to Deep Reinforcement Learning in JAX - Towards Data Science

A Gentle Introduction to Deep Reinforcement Learning in JAX  Towards Data Science

Distributed reinforcement learning of the Ape‐X DQN - researchgate.net

Distributed reinforcement learning of the Ape‐X DQN  researchgate.net

Proposed LSTM-DQN-epsilon-greedy system architecture. - researchgate.net

Proposed LSTM-DQN-epsilon-greedy system architecture.  researchgate.net

Figure 3: Architecture of CNN-attached duelling DQN - researchgate.net

Figure 3: Architecture of CNN-attached duelling DQN  researchgate.net

Part 2 - Building a deep Q-network to play Gridworld - Catastrophic Forgetting and Experience... ...

Part 2 - Building a deep Q-network to play Gridworld - Catastrophic Forgetting and Experience...  Towards Data Science

Research on time series prediction of multi-process based on deep learning - Nature

Research on time series prediction of multi-process based on deep learning  Nature

Figure 1: Concept of DQN Every time the replay memory has been updated,... - researchgate.net

Figure 1: Concept of DQN Every time the replay memory has been updated,...  researchgate.net

A Heuristically Accelerated Reinforcement Learning-Based Neurosurgical Path Planner - Science Par...

A Heuristically Accelerated Reinforcement Learning-Based Neurosurgical Path Planner  Science Partner Journals

Figure 5. The LSTM-DQN network structure. - researchgate.net

Figure 5. The LSTM-DQN network structure.  researchgate.net

FIGURE 3. DQN dynamic resource allocation model. - researchgate.net

FIGURE 3. DQN dynamic resource allocation model.  researchgate.net

The framework of deep Q network (DQN). - researchgate.net

The framework of deep Q network (DQN).  researchgate.net

Training the Lunar Lander Agent With Deep Q-Learning and Its variants - DataDrivenInvestor

Training the Lunar Lander Agent With Deep Q-Learning and Its variants  DataDrivenInvestor

FIGURE 2. The training process of DQN/D3QN. - researchgate.net

FIGURE 2. The training process of DQN/D3QN.  researchgate.net

Fig. 2: The structure of our Deep Q-Network (DQN) strategy - researchgate.net

Fig. 2: The structure of our Deep Q-Network (DQN) strategy  researchgate.net

Fig. 3: Deep Q-network (DQN) based MEC System - researchgate.net

Fig. 3: Deep Q-network (DQN) based MEC System  researchgate.net

FIGURE 7. DQN and A3C training algorithms. - researchgate.net

FIGURE 7. DQN and A3C training algorithms.  researchgate.net

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning - Frontiers

Pursuit and Evasion Strategy of a Differential Game Based on Deep Reinforcement Learning  Frontiers

Overview of training workflow. We employed the DQN algorithm to train... - researchgate.net

Overview of training workflow. We employed the DQN algorithm to train...  researchgate.net

Deep reinforcement learning-based long-range autonomous valet parking for smart cities - ScienceD...

Deep reinforcement learning-based long-range autonomous valet parking for smart cities  ScienceDirect.com

Part 1 – Building a deep Q-network to play Gridworld – DeepMind’s deep Q-networks - Towards Data ...

Part 1 – Building a deep Q-network to play Gridworld – DeepMind’s deep Q-networks  Towards Data Science

FIGURE 6 | Effects of the update frequency of the target network on the... - researchgate.net

FIGURE 6 | Effects of the update frequency of the target network on the...  researchgate.net

Optimization and analysis of distributed power carrying capacity of distribution network based on...

Optimization and analysis of distributed power carrying capacity of distribution network based on DR-DQN  Frontiers

Fig. 4 Learning curves based on the DQN, PPO, SAC and ORRL methods - researchgate.net

Fig. 4 Learning curves based on the DQN, PPO, SAC and ORRL methods  researchgate.net

Figure 6.1: Average evaluation reward of DQN in Breakout (each point is... - researchgate.net

Figure 6.1: Average evaluation reward of DQN in Breakout (each point is...  researchgate.net

Google's DeepMind Masters Atari Games - Forbes

Google's DeepMind Masters Atari Games  Forbes

DQ-HGAN: A heterogeneous graph attention network based deep Q-learning for emotional support conv...

DQ-HGAN: A heterogeneous graph attention network based deep Q-learning for emotional support conversation generation  ScienceDirect.com

Advanced DQNs: Playing Pac-man with Deep Reinforcement Learning - Towards Data Science

Advanced DQNs: Playing Pac-man with Deep Reinforcement Learning  Towards Data Science

A DOD-SOH balancing control method for dynamic reconfigurable battery systems based on DQN algori...

A DOD-SOH balancing control method for dynamic reconfigurable battery systems based on DQN algorithm  Frontiers

Figure 2: The Q-learning algorithm taken from Sutton & Barto (1998). - researchgate.net

Figure 2: The Q-learning algorithm taken from Sutton & Barto (1998).  researchgate.net

Figure 1. DQN and Averaged-DQN performance in the Atari game of... - researchgate.net

Figure 1. DQN and Averaged-DQN performance in the Atari game of...  researchgate.net

Figure 7: Bar Chart and Confusion Matrix for the base DQN algorithm for... - researchgate.net

Figure 7: Bar Chart and Confusion Matrix for the base DQN algorithm for...  researchgate.net

FIG. 4: The learning curve of a deep Q-network (DQN) with two hidden... - researchgate.net

FIG. 4: The learning curve of a deep Q-network (DQN) with two hidden...  researchgate.net

FIGURE 5. DQN agent's performance for different values of learning... - researchgate.net

FIGURE 5. DQN agent's performance for different values of learning...  researchgate.net

FIGURE 13 | Learning curves of Constrained DQN, DQN, DQN with TC-loss,... - researchgate.net

FIGURE 13 | Learning curves of Constrained DQN, DQN, DQN with TC-loss,...  researchgate.net

Google's Atari-Playing Algorithm Is the Future of AI - Popular Mechanics

Google's Atari-Playing Algorithm Is the Future of AI  Popular Mechanics

A Dynamic Adjusting Reward Function Method for Deep Reinforcement Learning with Adjustable Parame...

A Dynamic Adjusting Reward Function Method for Deep Reinforcement Learning with Adjustable Parameters  Wiley Online Library

FIGURE 9 | Learning curves of DQN (red), Q learning (green), DQN with... - researchgate.net

FIGURE 9 | Learning curves of DQN (red), Q learning (green), DQN with...  researchgate.net

FIGURE 4. DQN Reward Convergence - researchgate.net

FIGURE 4. DQN Reward Convergence  researchgate.net

Fig. 2: Deep Q-network (DQN) based trajectory design for autonomous... - researchgate.net

Fig. 2: Deep Q-network (DQN) based trajectory design for autonomous...  researchgate.net

A value-based deep reinforcement learning model with human expertise in optimal treatment of seps...

A value-based deep reinforcement learning model with human expertise in optimal treatment of sepsis  Nature