Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/ugurkanates/awesome-real-world-rl

Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.
https://github.com/ugurkanates/awesome-real-world-rl

List: awesome-real-world-rl

awesome awesome-list gans imitation-learning meta-learning reinforcement-learning robotics sim2real simulation

Last synced: 2 months ago
JSON representation

Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.

Lists

README 

        
# Awesome Real World RL [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)



> Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.  



![test](out.png)



This list is big compilation of all things trying to adapt Reinforcement Learning techniques in real world.Either it's mixing real world data into mix or trying to adapt simulations in a better way.It will also include some of Imitation Learning and Meta Learning along the way. If you have anything missing feel free to open a PR,I'm all for community contributions.  



## Contents



- [Papers](#papers)

- [Books](#books)

- [Conference Talks](#conference-talks)

- [Education](#education)

- [Simulation to Real with GANs](#simulation-to-real-with-gans)

- [Meta Reinforcement Learning](#meta-reinforcement-learning)

- [Imitation Learning](#imitation-learning)

- [Multi Agent in Real World](#multi-agent-in-real-world)

- [Real World Examples](#real-world-examples)

- [Offline RL](#offline-rl)

- [Datasets](#datasets)

- [Projects](#projects)

- [Libraries](#libraries)

- [Prominent Researchers & Companies to Follow](#prominent-researchers--companies-to-follow)



## Papers



Any academic work done related to RL in real world.This is the other part of list,anything doesn't fit but still related gets here.



- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://arxiv.org/abs/1703.06907)

- [Asymmetric Actor Critic for Image-Based Robot Learning](https://arxiv.org/abs/1710.06542)

- [Towards Learning Robots Which Can Adapt on the Fly](https://arxiv.org/abs/2004.10190)

- [Thinking while moving : Deep RL with Concurrent Control](https://sites.google.com/view/thinkingwhilemoving/home)

- [Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control](https://arxiv.org/abs/1511.03791)

- [Quantifying the Reality Gap in Robotic Manipulation Tasks](https://arxiv.org/abs/1811.01484)

- [Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task](https://arxiv.org/abs/1707.02267)

- [Sim-to-Real Robot Learning from Pixels with Progressive Nets](https://arxiv.org/abs/1610.04286)

- [A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning](https://arxiv.org/abs/1810.01531)

- [Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer](https://arxiv.org/abs/1910.09471)

- [Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers](https://arxiv.org/abs/2006.13916)

- [Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning](https://arxiv.org/abs/2004.12974)

- [The Ingredients of Real-World Robotic Reinforcement Learning](https://arxiv.org/abs/2004.12570)

- [Learning personalized treatments via IRL](https://arxiv.org/abs/1905.09710)

- [Reinforcement Learning Applications](https://arxiv.org/pdf/1908.06973.pdf)

- [Challenges of Real-World Reinforcement Learning](https://arxiv.org/abs/1904.12901)

- [An empirical investigation of the challenges of real-world reinforcement learning](https://arxiv.org/abs/2003.11881)

- [Generalized State-Dependent Exploration for Deep Reinforcement Learning in Robotics](https://arxiv.org/abs/2005.05719)

- [Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning](https://arxiv.org/abs/2004.12485)

- [Scaling simulation-to-real transfer by learning composable robot skills](https://arxiv.org/abs/1809.10253)

- [The Importance and the Limitations of Sim2Real for Robotic Manipulation in Precision Agriculture](https://sim2real.github.io/assets/papers/2020/rizzardo.pdf)

- [Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions](https://arxiv.org/abs/2007.02382)



## Books



Any book dedicated to RL in real world or book parts that contains related content.



- [Deep RL Hands On 2nd Edition Packt Edition](https://www.packtpub.com/data/deep-reinforcement-learning-hands-on-second-edition) - Has entire chapter dedicated to real world robotics agent.

- [Foundations of Deep Reinforcement Learning: Theory and Practice in Python](https://www.pearson.com/us/higher-education/program/Graesser-Foundations-of-Deep-Reinforcement-Learning-Theory-and-Practice-in-Python/PGM2027228.html) - Few chapters related to real world applications.



## Conference Talks



Any recorded talk related to subject goes here.



- [GPU Technology Conference 2017: Sim2real collision avoidance for indoor navigation of mobile robots](https://www.youtube.com/watch?v=qFmH4oZPlYY)

- [Reinforcement learning and it's growing role in AI with Real World examples - Microsoft 2020](https://youtu.be/Qahd9poQvLs)

- [RL in Real World 2020 Conference](https://sites.google.com/view/RL4RealLife)

- [RL for Real Life Panel Discussion June 27-28 2020](https://www.youtube.com/watch?v=lDdC8Gjat9w&feature=youtu.be)

- [RL for Health Care Panel Discussion June 28 2020](https://youtu.be/dDSENm2smkQ)

- [Learning to Dock Robustly](https://youtu.be/tlcAqwpxJUQ)

- [On Demand Ride Sharing with RL](https://underline.io/lecture/493-neural-approximate-dynamic-programming-for-on-demand-ride-pooling)

- [BADGR: An Autonomous Self-Supervised Learning-Based Navigation System](https://youtu.be/UtoZEwrDHj4)

- [An empirical investigation of the challenges of real world Reinforcement Learning](https://youtu.be/1d6bD084-hY)

- [Why Sim2Real ? - July 10 2020](https://www.youtube.com/watch?v=Q-rsvVr2CjE&list=PLKUnyDCkD3O_BHMiGuP7V38KEUSzVGJb0)

- [Visual Learning and Reasoning for Robotic Manipulation](https://rss2020vlrrm.github.io/)



## Education 



Free or paid courses related to subject goes here.



- [Stanford CS330 Meta RL + Multi Task by Chelsea Finn 2019-2020](https://www.youtube.com/watch?v=0rZtSwNOTQo)

- [CMU Real Life Reinforcement Learning 2015](https://www.cs.cmu.edu/~ebrun/15889e/index.html) - A lot of advanced topics as well as talks about DARPA RL Challenge.

- [Reinforcement Learning Robot Course CMPUT 652 Fall 2019](https://armahmood.github.io/rl-robots-course/)



## Simulation to Real with GANs



Any paper uses GANs to generate realistic simulation images for adaptation of policy goes here.



- [Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping - GraspGAN](https://arxiv.org/abs/1709.07857)

- [CycleGAN](https://junyanz.github.io/CycleGAN/)

- [RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real](https://arxiv.org/abs/2006.09001)



## Meta Reinforcement Learning



Anything Meta RL goes here.

- [Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks](https://arxiv.org/abs/2004.14404)

- [Sim-to-Real Transfer of Accurate Grasping with Eye-In-Hand Observations and Continuous Control​](https://research.nvidia.com/sites/default/files/pubs/2017-12_Sim-to-Real-Transfer-of/Sim-to-Real%20Transfer%20of%20Accurate%20Grasping%20with%20Eye-In-Hand%20Observations%20and%20Continuous%20Control.pdf)

- [Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling](https://arxiv.org/abs/2006.07178)



## Imitation Learning



Anything Imitation Learning goes here.



- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://arxiv.org/abs/1802.09564)

- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://arxiv.org/abs/2004.00784)



## Multi Agent in Real World



Anything Multi Agent Real World RL related goes here.



- [Python MARL](https://github.com/oxwhirl/pymarl)



## Real World Examples



Any real world news or projects deployed RL in real life goes here.Mostly news,comments,blog posts etc.



- [Reinforcement learning for the real world - Article](https://www.oreilly.com/radar/reinforcement-learning-for-the-real-world/)

- [Reinforcement Learning Applications in Real Life June 2019](https://medium.com/@yuxili/rl-applications-73ef685c07eb)



## Offline RL



Anything Offline Reinforcement Learning goes here.



- [Scaling data-driven robotics with reward sketching and batch reinforcement learning](https://arxiv.org/abs/1909.12200)

- [Accelerating Online Reinforcement Learning with Offline Datasets](https://arxiv.org/abs/2006.09359)

- [MOPO: Model-based Offline Policy Optimization](https://arxiv.org/abs/2005.13239)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://arxiv.org/abs/2005.01643)



## Datasets 



Saved datasets goes here.



- [RoboNet - Large Scale Multi Robot Learning](https://arxiv.org/pdf/1910.11215.pdf)

- [GQ-CNN Training Datasets](https://berkeley.app.box.com/s/6mnb2bzi5zfa7qpwyn7uq5atb7vbztng)

- [GQ-CNN Object Mesh Datasets](https://berkeley.app.box.com/s/w6bmvvkp399xtjpgskwq1cytkndmm7cn)

- [HDF5 Database of 3D Objects, Parallel-Jaw Grasps for YuMi, and Robustness Metrics](https://berkeley.app.box.com/s/eaq37px77jxktr8ggti016pr3gpudp9l)

- [Google Robotics Dataset](https://sites.google.com/site/brainrobotdata/home/) - Includes Grasping-Push-Depth Image-Pouring-3DModels.

- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://arxiv.org/abs/2004.07219)



## Projects



Any project link available on internet related to it goes here.



- [Dexterity Network - Grasp Quality Convolutional Neural Networks (GQ-CNN)](https://berkeleyautomation.github.io/dex-net/)



## Libraries



Open source libraries related goes to here.



- [State Representation Learning Zoo](https://github.com/araffin/srl-zoo) - Implements most of SRL algorithms in robotic settings.

- [Robotics Reinforcement Learning](https://github.com/araffin/robotics-rl-srl) - Customizable PyBullet gym robotic environment.

- [RL Bench](https://github.com/stepjam/RLBench) - Includes object oriented approaches for robotic RL tasks.

- [RL Garage](https://github.com/rlworkgroup/garage) - Includes common RL real world robotic benchmarks. 

- [RL Robotic Meta World - Robotic Manipulation Tasks](https://github.com/rlworkgroup/metaworld) - Real world examples regarding to Meta Learning.

- [GYM Sawyer Robot Environments - ROS](https://github.com/rlworkgroup/gym-sawyer) - Sawyer robot with ROS and RL.



## Prominent Researchers & Companies to Follow



- [Sergey Levine](https://twitter.com/svlevine?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor) - Google Robotics,UC Berkeley.

- [Chelsea Finn](https://twitter.com/chelseabfinn?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor) - Stanford Uni,Google Brain.

- [Ashvin Nair](http://ashvin.me/) - UC Berkeley.

- [99andBeyond](https://99andbeyond.com/) - Chemical Company Uses RL for Research,Biomedical & Chemistry.

- [Google Brain & Robotics](https://research.google/teams/brain/) - Mostly Real Life RL Robotics projects.

- [X Company](https://x.company/) - A lot of physics and real life based problems with RL.

- [Damien Ernst](https://scholar.google.com/citations?user=91ZxYSsAAAAJ&hl=en) - Real Life solutions to energy related problems.

- [Xinyang Geng](https://scholar.google.com/citations?user=vYougn0AAAAJ&hl=en) - A lot of Meta Learning and locomotion RL.

- [Maxim Lapan](https://github.com/Shmuma) - Author of Deep RL Hands-On book.

- [Scott Fujimoto](https://scholar.google.com/citations?user=1Nk3WZoAAAAJ&hl=en) - One of the most prominent Offline RL researcher.

- [TalkRL Podcast](www.talkrl.com) - Includes a lot of new RL research.



## Contribute



Contributions welcome! Read the [contribution guidelines](contributing.md) first.



To the extent possible under law, Ugurkan Ates has waived all copyright and

related or neighboring rights to this work.



Contributors: Ugurkan Ates