ManiSkill is a benchmark platform for training and evaluating reinforcement learning agents on dexterous manipulation tasks using physics-based simulations. Developed by Hao Su Lab, it focuses on robotic manipulation with diverse, high-quality 3D tasks designed to challenge perception, control, and planning in robotics. ManiSkill provides both low-level control and visual observation spaces for realistic learning scenarios.

Features

  • Includes a diverse set of dexterous manipulation tasks and scenarios
  • Offers both low-dimensional state and high-dimensional visual observations
  • Supports physics-based simulation using the Isaac Gym engine
  • Compatible with common RL algorithms and libraries like Stable-Baselines3
  • Provides standardized benchmarks for robotic manipulation research
  • Facilitates multi-task learning and generalization across tasks

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow ManiSkill

ManiSkill Web Site

Other Useful Business Software
Full-stack observability with actually useful AI | Grafana Cloud Icon
Full-stack observability with actually useful AI | Grafana Cloud

Our generous forever free tier includes the full platform, including the AI Assistant, for 3 users with 10k metrics, 50GB logs, and 50GB traces.

Built on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
Create free account
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of ManiSkill!

Additional Project Details

Programming Language

Python

Related Categories

Python Reinforcement Learning Frameworks

Registered

2025-03-13