d3qn 开源项目推荐（24 个）

germain-hug /Deep-RL-Keras

Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)

pythonlessons /Reinforcement_Learning

Reinforcement learning tutorials

ImanRHT /QECO

基于深度强化学习（DRL）的面向QoE计算卸载算法，适用于移动边缘计算（MEC）|该算法通过将双重深度Q网络（D3QN）模型与长短期记忆（LSTM）网络集成，捕捉了MEC环境的动态。

DanielPalaio /LunarLander-v2_DeepRL

基于深度强化学习的 OpenAI LunarLander-v2 解决方案（DQN、DuelingDQN、D3QN）

DanielPalaio /MountainCar-v0_DeepRL

基于深度强化学习的 OpenAI MountainCar-v0 解决方案（DQN、DuelingDQN、D3QN）

MahanVeisi8 /RL_practices

Collection of my Reinforcement Learning (RL) practices including DQN, D3QN, and Adaptive Gamma, applied to the Lunar Lander and CartPole environments. 🚀🕹️

negarhonarvar /DeepReinforcementLearning

A Complete Collection of Deep RL Famous Algorithms implemented in Gymnasium most Popular environments

Amirarsalan-sn /Lunar-Lander

Lunar Lander envitoment of gymnasium solved using Double DQN and D3QN

DanielPalaio /Pong-v4_DeepRL

Atari OpenAI Pong-v4 DeepRL-based solutions (DQN, DuelingDQN, D3QN)

DanielPalaio /CartPole-v0_DeepRL

OpenAI CartPole-v0 DeepRL-based solutions (DQN, DuelingDQN, D3QN)

navidadkhah /LunaLander-v2

Lunar Lander envitoment of gymnasium solved using DQN and D3QN

shiroonigami23-ui /omega

Beautiful modular D3QN research pipeline with training, ablations, plots, report, and packaging

HenZ-111 /SeqDRL-Detection

A project to classification.

dadadadawjb /RLDemo

Reinforcement Learning Demo: DQN with D3QN and DDPG with TD3 PyTorch re-implementation on Atari and MuJoCo

EnriqManComp /Lunar-Lander-DRL-Dueling-DoubleDQN

This is a Deep Reinforcement Learning solution for the Lunar Lander problem in OpenAI Gym using dueling network architecture and the double DQN algorithm.

Flahhhh /D3QN

This is D3QN implementation for simple environment

mayanzu /ECB-HD-CR

Reproducible simulations for ECB-HD-CR: energy-credit scheduling and routing in energy-harvesting wireless sensor networks.

JoshiMinh /lunar-lander-rl

A deep reinforcement learning project built with PyTorch and Gymnasium, featuring a custom VastSpaceLander environment and a Dueling Double DQN agent for fuel-efficient, high-precision landing under extreme gravity conditions.

emanuelegreco29 /RL_Dogfighting_Toy_Model

Toy Model implemention to train a Reinforcement Learning Agent for Within Visual Range (WVR) aerial combat.

saharlynds /dqn-d3qn-lunarlander

DQN vs Dueling Double DQN (D3QN) on LunarLander-v2 with hard/soft target sync and gamma annealing experiments