A curated collection of resources focused on Machine Learning applications in robotics. It targets researchers, engineers, and practitioners seeking to leverage ML for complex robotic tasks, offering a centralized, organized overview of key papers, software implementations, and simulation tools to accelerate development and research in the field.

How It Works

The project operates by systematically indexing and categorizing seminal academic papers and practical implementations relevant to machine learning in robotics. Resources are grouped under thematic headings such as Learned Approximate Inference, Deep Reinforcement Learning, Policy Gradients, and Meta-Learning, providing a structured pathway to discover foundational research and state-of-the-art tools.

Quick Start & Requirements

This repository is a curated list of external resources and does not include runnable code or direct installation instructions.

Highlighted Details

• Features foundational papers in areas like Variational Inference (e.g., Kingma et al., Rezende et al.) and Reinforcement Learning (e.g., Mnih et al., Lillicrap et al., Sutton et al.).
• Lists critical ML for robotics implementations including OpenAI Gym, OpenAI baselines, Keras-RL, and Deepmind DQN.
• Includes prominent robotic simulators like MuJoCo, Gazebo, and V-REP, alongside the open-source Poppy robotic platform.

Maintenance & Community

The list is curated by Alexandre Pere and Pierre Manceron. The README does not provide links to community channels (e.g., Discord, Slack) or a project roadmap.

Licensing & Compatibility

The README does not specify a license for the curated list itself. Users must consult the individual licenses of each linked paper, code repository, and simulator for compatibility, especially concerning commercial use or closed-source integration.

Limitations & Caveats

This resource is a static index and does not offer executable code, direct setup guides, or performance benchmarks for the listed items. The update frequency and maintenance status of the curation are not specified. Users are responsible for independently verifying the licensing and current status of each referenced external resource.