Massively Parallel Deep Reinforcement Learning. 🔥

Builds ONNX Runtime for ARMv7 using a bootlin musl toolchain

自动驾驶规划控制python代码实现

[IROS 2023] Continuous Implicit SDF Based Any-shape Robot Trajectory Optimization

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

An Efficient Multi-Agent Path Finding Solver for Car-Like Robots

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

Implementation of the paper "Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning"

Refer to https://github.com/AcutronicRobotics/gym-gazebo2 for the new version

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。