├── .gitignore ├── README.md └── rsc └── contributing.jpg /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome Model-based Reinforcement Learning[![Awesome](https://awesome.re/badge.svg)](https://awesome.re) 2 | 3 | 6 | 7 | A curated list of awesome Model-based Reinforcement Learning resources. Inspired by [awesome-deep-vision](https://github.com/kjw0612/awesome-deep-vision), [awesome-adversarial-machine-learning](https://github.com/yenchenlin/awesome-adversarial-machine-learning), [awesome-deep-learning-papers](https://github.com/terryum/awesome-deep-learning-papers), and [awesome-architecture-search](https://github.com/markdtw/awesome-architecture-search) 8 | 9 | Model-based Reinforcement Learning is gaining popularity in Robotics community. These are some of the awesome resources! 10 | 11 |

12 | 13 |

14 | 15 | ## Contributing 16 | Please help contribute this list by adding [pull request](https://github.com/hjzh4/awesome-model-based-reinforcement-learning/pulls) 17 | 18 | Markdown format: 19 | ```markdown 20 | - Paper Name [[pdf]](link) [[code]](link) 21 | - Author 1, Author 2 and Author 3. *Conference/Journal Year* 22 | ``` 23 | 24 | ## Table of Contents 25 | - [Thesis](#thesis) 26 | - [Survey](#survey) 27 | - [Conference Papers](#conference_papers) 28 | - [Journal Papers](#journal_papers) 29 | - [Tutorials](#tutorials) 30 | - [Tools](#tools) 31 | 32 | ## Thesis 33 | - Efficient Reinforcement Learning using Gaussian Processes. [[pdf]](https://pdfs.semanticscholar.org/c9f2/1b84149991f4d547b3f0f625f710750ad8d9.pdf) 34 | - Marc Peter Deisenroth. 35 | ## Survey 36 | #### 2017 37 | - Survey of Model-Based Reinforcement Learning: Applications on Robotics. [[pdf]](https://link.springer.com/article/10.1007/s10846-017-0468-y) 38 | - Athanasios S. Polydoros and Lazaros Nalpantidis. *J Intell Robot Syst 2017* 39 | ## CV/CG 40 | - Curiosity-driven Exploration by Self-supervised Prediction. [[pdf]](https://arxiv.org/pdf/1705.05363.pdf) [[code]](https://github.com/pathak22/noreward-rl) 41 | - Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell. *ICML 2017* 42 | ## Conference Papers 43 | ### Physics Model 44 | - Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning. [[pdf]](http://www.roboticsproceedings.org/rss14/p44.pdf) [[code]](https://github.com/MarcToussaint/18-RSS-PhysicalManipulation) 45 | - Marc Toussaint, Kelsey R. Allen, Kevin A. Smith, Joshua B. Tenenbaum. *RSS 2018* 46 | - A convex, smooth and invertible contact model for trajectory optimization. [[pdf]](https://homes.cs.washington.edu/~todorov/courses/amath533/ContactConvex.pdf) 47 | - Emanuel Todorov. *ICRA 2011* 48 | - A Modular Differentiable Rigid Body Physics Engine. [[pdf]](https://drive.google.com/file/d/1K8t4gQExFXbuG4F9Zd2_30Y5wtpdEST7/view) [[code]](https://github.com/locuslab/lcp-physics) 49 | - Filipe de Avila Belbute-Peres, J. Zico Kolter. *Deep Reinforcement Learning Symposium, NIPS 2017* 50 | - A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS. [[pdf]](https://openreview.net/pdf?id=HkrB8XXte) 51 | - Jonas Degrave, Michiel Hermans, Joni Dambre, Francis wyffels. *ICLR 2017* 52 | - Discovery of Complex Behaviors through Contact-Invariant Optimization. [[pdf]](https://homes.cs.washington.edu/~todorov/papers/MordatchSIGGRAPH12.pdf) 53 | - Igor Mordatch, Emanuel Tordorov, Zoran Popovic. *TOG'12* 54 | ### Hybrid model-based and model-free algorithm 55 | - Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. [[pdf]](https://arxiv.org/abs/1708.02596) [[code]](https://github.com/nagaban2/nn_dynamics) 56 | - Anusha Nagabandi, Gregory Kahn, Ronald S. Fearing, Sergey Levine. 57 | - Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning. [[pdf]](https://arxiv.org/abs/1703.03078) 58 | - Yevgen Chebotar, Karol Hausman, Marvin Zhang, Gaurav Sukhatme, Stefan Schaal, Sergey Levine. *ICML 2017* 59 | ### Optimal Control 60 | - Local Gaussian Process Regression for Real-time Model-based Robot Control. [[pdf]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4650850) 61 | - Duy Nguyen-Tuong and Jan Peters. *IROS 2008* 62 | ### Local model 63 | - Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics. [[pdf]](https://people.eecs.berkeley.edu/~svlevine/papers/mfcgps.pdf) [[code]](https://github.com/cbfinn/gps/blob/master/docs/index.md) 64 | - Sergey Levine and Pieter Abbeel. *NIPS 2014* 65 | ### Learn in latent space 66 | #### Foward Dynamics Model 67 | - Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images. [[pdf]](https://arxiv.org/pdf/1506.07365.pdf) [[code]](https://github.com/ericjang/e2c) 68 | - Manuel Watter, Jost Tobias Springenberg, Martin Riedmiller, Joschka Boedecker. *ICRA 2017* 69 | - Deep Spatial Autoencoders for Visuomotor Learning. [[pdf]](https://arxiv.org/pdf/1509.06113.pdf) [[code]](https://github.com/cbfinn/gps/blob/master/docs/index.md) 70 | - Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel. *ICRA 2016* 71 | ### Gaussian Process 72 | - Data-Efficient Reinforcement Learning in Continuous-State POMDPs. [[pdf]](https://papers.nips.cc/paper/6799-data-efficient-reinforcement-learning-in-continuous-state-action-gaussian-pomdps.pdf) 73 | - Rowan McAllister, Carl Rasmussen. *NIPS 2017* 74 | - Improving PILCO with Bayesian Neural Network Dynamics Models. [[pdf]](http://mlg.eng.cam.ac.uk/yarin/PDFs/DeepPILCO.pdf) 75 | - Yarin Gal and Rowan Thomas McAllister and Carl Edward Rasmussen. *Data-Efficient Machine Learning workshop, ICML, 2016* 76 | - PILCO: A Model-Based and Data-Efficient Approach to Policy Search. [[pdf]](http://mlg.eng.cam.ac.uk/pub/pdf/DeiRas11.pdf) [[code]](http://mlg.eng.cam.ac.uk/pilco/) [[unofficial code]](https://github.com/nrontsis/PILCO) 77 | - Marc Peter Deisenroth, Carl Rasmussen. *ICML 2011* 78 | - Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning. [[pdf]](http://www.roboticsproceedings.org/rss07/p08.pdf) 79 | - Marc Peter Deisenroth, Carl Edward Rasmussen and Dieter Fox. *RSS 2011* 80 | - Learning Dynamics Across Similar Spatiotemporally-Evolving Physical Systems. [[pdf]](http://proceedings.mlr.press/v78/whitman17a/whitman17a.pdf) 81 | - Joshua Whitman, Girish Chowdhary. *CoRL 2017* 82 | ## Journal Papers 83 | ## Tutorials 84 | - Deep RL Bootcamp Lecture 9 Model-based Reinforcement Learning. Chelsea Finn (UC Berkeley) [[link]](https://www.youtube.com/watch?v=iC2a7M9voYU) 85 | - Highlight Talk: Gaussian Processes for Data Efficient Learning. Marc Diesenroth [[link]](https://www.youtube.com/watch?v=dWsjjszwfi0) 86 | ## Tools 87 | - [GPFlow](https://github.com/GPflow/GPflow) 88 | - [GPy](https://github.com/SheffieldML/GPy) 89 | ## License 90 | To the extent possible under law, we have waived all copyright and related or neighboring rights to this work. 91 | -------------------------------------------------------------------------------- /rsc/contributing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hejia-zhang/awesome-model-based-reinforcement-learning/5ef10dde31588ec39c31fe65da3c30808af72e3d/rsc/contributing.jpg --------------------------------------------------------------------------------