https://github.com/blutjens/maml_rl
Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Science Score: 20.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
✓Committers with academic emails
4 of 16 committers (25.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.2%) to scientific vocabulary
Keywords from Contributors
Repository
Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Model-Agnostic Meta-Learning
This repo contains code accompaning the paper, Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (Finn et al., ICML 2017). It includes code for running the few-shot reinforcement learning experiments.
For the experiments in the supervised domain, see this codebase.
Dependencies
This code is based off of the rllab code repository and can be installed in the same way (see below). This codebase is not necessarily backwards compatible with rllab.
The MAML code uses the TensorFlow rllab version, so be sure to install TensorFlow v1.0+.
Usage
Scripts for running the experiments found in the paper are located in maml_examples/.
The pointmass environment is located in maml_examples/ whereas the MuJoCo environments are located in rllab/envs/mujoco/.
Speed of Code
One current limitation of the code is that it is particularly slow. We welcome contributions to speed it up. We expect the biggest speed improvements to come from better parallelization of sampling and meta-learning graph computation.
Contact
To ask questions or report issues, please open an issue on the issues tracker.
rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms. It includes a wide range of continuous control tasks plus implementations of the following algorithms:
- REINFORCE
- Truncated Natural Policy Gradient
- Reward-Weighted Regression
- Relative Entropy Policy Search
- Trust Region Policy Optimization
- Cross Entropy Method
- Covariance Matrix Adaption Evolution Strategy
- Deep Deterministic Policy Gradient
rllab is fully compatible with OpenAI Gym. See here for instructions and examples.
rllab only officially supports Python 3.5+. For an older snapshot of rllab sitting on Python 2, please use the py2 branch.
rllab comes with support for running reinforcement learning experiments on an EC2 cluster, and tools for visualizing the results. See the documentation for details.
The main modules use Theano as the underlying framework, and we have support for TensorFlow under sandbox/rocky/tf.
Documentation
Documentation is available online: https://rllab.readthedocs.org/en/latest/.
Citing rllab
If you use rllab for academic research, you are highly encouraged to cite the following paper:
- Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel. "Benchmarking Deep Reinforcement Learning for Continuous Control". Proceedings of the 33rd International Conference on Machine Learning (ICML), 2016.
Credits
rllab was originally developed by Rocky Duan (UC Berkeley / OpenAI), Peter Chen (UC Berkeley), Rein Houthooft (UC Berkeley / OpenAI), John Schulman (UC Berkeley / OpenAI), and Pieter Abbeel (UC Berkeley / OpenAI). The library is continued to be jointly developed by people at OpenAI and UC Berkeley.
Slides
Slides presented at ICML 2016: https://www.dropbox.com/s/rqtpp1jv2jtzxeg/ICML2016benchmarkingslides.pdf?dl=0
Owner
- Name: Björn Lütjens (he/him)
- Login: blutjens
- Kind: user
- Company: MIT
- Website: https://blutjens.github.io/
- Twitter: bjornlutjens
- Repositories: 31
- Profile: https://github.com/blutjens
Postdoctoral Associate in tackling climate change with AI @ MIT. Project overview at https://blutjens.github.io/
GitHub Events
Total
Last Year
Committers
Last synced: about 2 years ago
Top Committers
| Name | Commits | |
|---|---|---|
| Rocky Duan | d****k@g****m | 62 |
| Chelsea Finn | c****n@e****u | 48 |
| Chelsea Finn | c****m@g****m | 30 |
| Rocky Duan | d****k | 10 |
| florensacc | f****c@b****u | 6 |
| Alex Beloi | a****i | 2 |
| Alex Beloi | a****i@s****m | 2 |
| Paul Hendricks | p****3@o****u | 1 |
| David Held | d****d@e****u | 1 |
| OpenAI server | s****s@o****m | 1 |
| Zhongwen Xu | z****u@g****m | 1 |
| singulaire | t****u@g****m | 1 |
| Ben | c****n | 1 |
| lchenat | l****t@c****k | 1 |
| chang cheng | m****a@g****m | 1 |
| Xiaohu Zhu | x****u@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: about 2 years ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- ubuntu 16.04 build
- Cython *
- Lasagne 484866cf8b38d878e92d521be445968531646bb8
- Pillow *
- PyOpenGL *
- Theano adfe319ce6b781083d8dc3200fb4481b00853791
- atari-py *
- awscli *
- boto3 *
- cached_property *
- chainer ==1.15.0
- ipdb *
- jupyter *
- line_profiler *
- msgpack-python *
- mujoco_py *
- nose2 *
- plotly 2594076e29584ede2d09f2aa40a8a195b3f3fc66
- progressbar2 *
- pyglet *
- pyprind *
- pyzmq *
- activesupport >= 0
- pry >= 0
- activesupport 4.1.8
- coderay 1.1.0
- i18n 0.7.0
- json 1.8.1
- method_source 0.8.2
- minitest 5.5.1
- pry 0.10.1
- slop 3.6.0
- thread_safe 0.3.4
- tzinfo 1.2.2