MrLeedom / Reinforcement_LearningLinks
强化学习相关知识的学习，Ｑ学习和SARSA以及后面的DQN，有用到路径规划方面的，也有实际小迷宫的案例
☆35Updated 6 years ago
Alternatives and similar repositories for Reinforcement_Learning
Users that are interested in Reinforcement_Learning are comparing it to the libraries listed below
Sorting:
- 路径规划强化学习☆55Updated 5 years ago
- Deep reinforcement learning☆46Updated 3 years ago
- Deep reinforcement learning (DQN) implements robot path planning☆15Updated 5 years ago
- ☆43Updated 3 years ago
- 深度强化学习路径规划, SAC-Auto路径规划, Soft Actor-Critic算法, SAC-pytorch，激光雷达Lidar避障，激光雷达仿真模拟，Adaptive-SAC☆436Updated last year
- Path Planning for the Robots Using Reinforcement Learning☆38Updated 3 years ago
- Deep Reinforcement Learning based Adaptive Real-time Path Planning for UAV☆319Updated 3 years ago
- ☆13Updated 4 years ago
- 基于ppo的路径规划☆47Updated 2 years ago
- ☆81Updated 8 years ago
- learning the weight of each paras in DWA(Dynamic Window Approach) by using DQN(Deep Q-Learning)☆81Updated 7 years ago
- 本科毕业设计---使用多智能体强化学习的方法完成路径规划任务，要求路径优化和期间不碰撞，最后可视化整个行动过程☆18Updated 5 months ago
- Demonstrate the Q-Learning approach for AGV path planning☆45Updated 6 years ago
- ☆47Updated 4 years ago
- A leader-follower formation control using deep reinforcement learning environment, In which every agent can learn to follow the leader ag…☆51Updated 2 years ago
- -A framework for path-planing and obstacle avoidance using Deep Reinforcement Learning Techniques☆32Updated 5 years ago
- Multi agent scalable reinforcement learning for formation control with collision avoidance☆44Updated 10 months ago
- 多智能体均匀多边形编队、追逐与合围。☆49Updated 2 years ago
- DDPG algorithm for PID tuning☆29Updated 5 years ago
- 路径规划算法，A*，A-star启发搜索，Hybrid-A*，混合A*算法，Dijkstra迪杰斯特拉算法，GBFS贪婪最佳优先搜索算法，DFS深度优先搜索，BFS广度优先搜索算法等，车辆路径规划算法，小黑子路径规划☆347Updated 2 years ago
- 本项目重点完成了合同网模型的改进，并将其应用于飞行器任务的实时分配。飞行器中段飞行时间长，弹道固定，容易成为防御系统拦截重点。利用深度强化学习算法结合动态窗口局部路径规划法完成深度强化学习模型设计、飞行器突防航迹推演等关键技术研究。主要技术：CNP、DQN。☆20Updated 3 years ago
- Multi-agent-path-planning by Python,with 4 entrances, 4 target and 8 AGVs☆27Updated 3 years ago
- This is a UAV path planning in a map-based environment using double deep Q-Network☆36Updated last year
- Robot path planning in static and dynamic environment (GSA, artificial potential field, QL, DDQL)☆40Updated 5 years ago
- 本代码的实现包括两个部分： 第一部分： 基于人工势场法的机器人路径规划：随机生成12-15个障碍物，每个障碍物随机占据6-20个栅格，利用该人工势场法编程实现机器人从左下到右上的路径规划。 同时在代码中已实现动态展示的效果。 第二部分： …☆160Updated 4 years ago
- 利用深度强化学习的方法实现多智能体间离散无交流的障碍避免。其中强化学习算法训练模型所需的数据集由最优互惠碰撞避免(Optimal Reciprocal Collision Avoidance， ORCA)算法生成。☆88Updated 6 years ago
- 基于粒子群算法多无人机任务分配☆143Updated 5 years ago
- 复现一篇在网格环境中使用改进Q-learning进行路径规划的论文☆20Updated 2 years ago
- 用于多机覆盖路径规划流程化算法 Algorithm for Streamlining Multi-Agent Coverage Path Planning☆65Updated 2 years ago
- This is the the partial code for my thesis. A COLREGS-compliant multiship collision avoidance based on deep reinforcement learning☆12Updated last year