MLtaotao / Udacity_P4_SmartcabLinks
应用强化学习在复杂的交通环境下自动学习最佳驾驶策略的方案,在测试环境下准确率达到100%。
☆19Updated 8 years ago
Alternatives and similar repositories for Udacity_P4_Smartcab
Users that are interested in Udacity_P4_Smartcab are comparing it to the libraries listed below
Sorting:
- Reinforcement Learning in Python☆107Updated 5 years ago
- Deep reinforcement learning agents implement by tensorflow https://ghli.org☆53Updated 5 years ago
- ☆20Updated 7 years ago
- reinforcement learning ddpg code. follow deepmind papers.☆60Updated 7 years ago
- Collection of Deep Reinforcement Learning algorithms☆124Updated 8 years ago
- ☆53Updated 8 years ago
- RL library based on algorithms from the book <A-introduction-to-reinforcement-learning>☆90Updated 7 years ago
- 根据隐马尔科夫原理,依据Q-learning的加强学习算法, 构建一个能够自学习交通规则 并且能够经过加强学习训练之后 找到最佳规划路线 并且能在规定时间到达. 目前优化后的成功率达到99%. 这个是自动驾驶路线规划的重要部分.☆8Updated 8 years ago
- Torcs-DQN implementaion☆14Updated 7 years ago
- 一个单路口交通信号灯控制的SUMO环境demo☆13Updated 7 years ago
- 使用pytorch构建深度强化学习模型DQN☆25Updated 7 years ago
- A Toolbox for deep reinforcement learning(QLearning)☆38Updated 6 years ago
- A translation of Reinforcement Learning: An Introduction☆114Updated 6 years ago
- 多智能体即时策略对抗方法与实践 苏炯铭 刘鸿福 陈少飞 项凤涛 编著 科学出版社 2019.11 随书代码☆31Updated 4 years ago
- 引用整理https://blog.csdn.net/yellow_red_people/article/details/80465510 一文中PyTorch平台,利用DQN模型玩Flappy Bird游戏,是一个再励学习(强化学习)实验例子。☆47Updated 6 years ago
- Deep Recurrent Attention Reinforcement Learning in Atari☆85Updated 6 years ago
- Reinforcement learning of driving a racing car in TORCS using DDPG algorithm☆14Updated 7 years ago
- 使用深度强化学习解决视觉跟踪和视觉导航问题☆25Updated 4 years ago
- 使用深度学习的方法,给特斯拉汽车学习端对端的自动驾驶,本项目利用MIT 6.S094 这门公开课中的Tesla数据集训练深度学习模型,根据车辆的前置相机所拍摄的路况图像,实现对车辆转向角度的预测。(本项目还未完成)☆50Updated 3 years ago
- ☆45Updated 5 years ago
- 用强化学习来玩微信跳一跳☆19Updated 7 years ago
- A Reinforcement Learning algorithm that drives a self driving car☆56Updated 7 years ago
- Models built with TensorFlow☆34Updated 7 years ago
- ☆390Updated 4 years ago
- 硕士毕设,基于强化学习的足型机器人运动控制☆11Updated 6 months ago
- This code is written for the blogs☆271Updated 8 years ago
- Alignment成为GPT类大模型微调的必须环节,深度强化学习是Alignment的核心。本项目是一个支持非gym环境训练、支持可视化配置的深度强化学习应用编程框架,30分钟上手强化学习编程。☆73Updated 2 years ago
- Tensorflow + OpenAI Gym implementation of Deep Q-Network (DQN), Double DQN (DDQN), Dueling Network and Deep Deterministic Policy Gradient…☆77Updated 8 years ago
- Series Algorithms of Deep Reinforcement Learning, such as DQN, DDQN, one-step-DQN, DDPG, etc☆43Updated 8 years ago
- Practice of Deep Reinforcement Learning with Keras and gym.☆158Updated 6 years ago