AlphaZero vs Dueling Double DQN on 5x5 Dots & Boxes. Same board, same features, measured head-to-head with search disabled on both sides.
-
Updated
Oct 7, 2026 - Python
#
deep-q-network
Here are 539 public repositories matching this topic...
🐍 Snake game trained with Deep Q-Network (DQN) using PyTorch and Pygame
-
Updated
Oct 5, 2026 - Python
A Double Deep Q-Network (DDQN) reinforcement learning algorithm to train a Battlesnake agent. Several features are used to enhance the algorithm, including vectorized environments, prioritized experience replay, board canonicalization, self-play, and a Monte Carlo Tree Search.
python training agent machine-learning neural-network simulation deep-reinforcement-learning pytorch artificial-intelligence deep-q-network monte-carlo-tree-search battlesnake dueling-network-architecture prioritized-experience-replay self-play double-deep-q-network vectorized-environments
-
Updated
Oct 5, 2026 - Python
Multi-cloud resource optimizer — XGBoost demand forecasting + Deep Q-Network autoscaling across AWS, Azure & GCP, with Isolation Forest anomaly detection and SHAP explanations. FastAPI · React
react reinforcement-learning xgboost cloud-computing autoscaling deep-q-network multi-cloud anomaly-detection shap fastapi
-
Updated
Oct 5, 2026 - Python
Highway-env reinforcement learning workspace with DQN training and a versioned TorchScript policy service.
-
Updated
Oct 5, 2026 - Python
SAVI: autonomous real-estate valuation agent for Ames, Iowa — XGBoost AVM + RL (Value Iteration, Q-Learning, Double DQN) on an event-driven AWS pipeline (S3·Lambda·EC2·SageMaker) with a live RAG agent web app
real-estate aws machine-learning reinforcement-learning aws-lambda pytorch xgboost deep-q-network sagemaker rag mlops llm-agent
-
Updated
Oct 3, 2026 - Python
Undergraduate thesis: a DQN agent learns C-V2X sidelink congestion control, and the learned policy is read back out as an explicit density-based rule. GPL-3.0 derivative of WiLabV2Xsim.
reinforcement-learning simulation matlab deep-q-network v2x congestion-control c-v2x wireless-networks
-
Updated
Oct 3, 2026 - MATLAB
Deep Q-Network agent for Gymnasium CarRacing with PyTorch, replay memory and frame preprocessing.
-
Updated
Oct 2, 2026 - Python
Applying Deep Reinforcement Learning for Gridworld Best-Route Navigation
exploratory-data-analysis cross-validation gridworld deep-q-network adam-optimizer huber-loss-regression on-policy off-policy accuracy-metrics randomized-search deep-double-q-network deep-expected-sarsa-network
-
Updated
Oct 5, 2026 - Python
Multi-agent Deep RL (Double+Dueling DQN + PER) for adaptive traffic signal control on a 2x2 grid, with SUMO and built-in simulators, emergency-vehicle preemption and a real-time dashboard.
python reinforcement-learning dqn sumo deep-q-network capstone-project prioritized-experience-replay traffic-signal-control intelligent-transportation multi-agent-rl
-
Updated
Oct 2, 2026 - Python
Reproducible DQN and Double DQN agents for Udacity Unity Navigation, with multi-seed evaluation and demo.
-
Updated
Oct 1, 2026 - Python
Deep Q-Network experience replay buffer and Polyak target network averaging engine
reinforcement-learning mcp q-learning dqn deep-q-network python-standard-library replay-buffer target-network temporal-difference agent-skills polyak-averaging
-
Updated
Sep 28, 2026 - Python
Deep Q-Network experience replay buffer and Polyak target network averaging engine
reinforcement-learning mcp q-learning dqn deep-q-network python-standard-library replay-buffer target-network temporal-difference agent-skills polyak-averaging
-
Updated
Sep 28, 2026 - Python
Reinforcement learning on CartPole, written out end to end: environment, agent, training loop and evaluation, as a readable reference rather than a one-file demo.
-
Updated
Sep 27, 2026 - Python
Snake as an RL environment in PyGame, plus an unfinished Deep Q-Network agent (2023)
-
Updated
Sep 20, 2026 - Python
Double-DQN HVAC controller for a smart building, trained on real 2024 Octopus Agile half-hourly tariff and Open-Meteo temperature data. Benchmarked against a hysteresis thermostat and random policy with paired significance testing over 73 held-out days.
python reinforcement-learning pytorch dqn deep-q-network gymnasium double-dqn smart-grid demand-response energy-management building-energy hvac-control octopus-energy smart-buildings time-of-use
-
Updated
Sep 20, 2026 - Python
PyTorch replication of Wang et al. (2018) "Deep Reinforcement Learning for Dynamic Multichannel Access." DQN vs. the analytical optimal policy on the round-robin switching case
reinforcement-learning pytorch deep-q-network pomdp wireless-networks paper-replication dynamic-spectrum-access
-
Updated
Sep 19, 2026 - Python
Snake agent trained with Double DQN in PyTorch.
-
Updated
Sep 17, 2026 - Python
Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision processes to predict future game states https://github.com/lucylow/MahjongArenaMobileAppDesign
nlp markov-model mahjong reinforcement-learning computer-vision reactjs tensorflow game-development markov-chain supervised-learning game-theory deep-q-network reinforcement softmax supervised-machine-learning npc-generator deep-neural-network deep-learning-mahjong battle-mahjong game-play
-
Updated
Sep 16, 2026 - TypeScript
A DQN that learned Ms. Pac-Man: mean score 492 to 2578 across five fixed evaluation games, with the evidence behind every claim.
-
Updated
Sep 15, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the deep-q-network topic, visit your repo's landing page and select "manage topics."