The repository is for safe reinforcement learning baselines.
- reinforcement-learning
- baseline
- robotics
- safe-reinforcement-learning
132,241 visible repositories in the index
73–96 of 96 · Most stars
The repository is for safe reinforcement learning baselines.
Set of robotic environments based on PyBullet physics engine and gymnasium.
人机模拟器(Human-vehicle Simulator)
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
[ICRA] Crowd-aware Robot Navigation
Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
ROS package for dynamic obstacle avoidance for ground robots trained with deep RL
🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
Published on Nature Machine Intelligence! The first real robot(quadrotor) based on differentiable physics training.
The GIMX software.
Deploy walk-these-ways project on Unitree Go2
A unified framework for robot learning
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
Dream to Control: Learning Behaviors by Latent Imagination
Pedestrian simulator powered by the social force model
Translated🦆 Feetech HD1910 Microduck replica: one-legged balance, ready-to-use models, Chinese console, custom HAT/IMU & 3-step build guides. No training required.
Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).
A high-performance, general-purpose toolkit for versatile robotic tasks.
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
OrcaSlicer with nonplanar top surfaces for macOS on Apple Silicon (test release)
Simple access to the g-force linear acceleration, gauss magnetic and dps angular rate sensors of the LSM9DS0 through I2C.
Sunrise and sunset time computation for MicroPython