Metadata-Version: 2.0 Name: Surreal Version: 0.1.1 Summary: Stanford University Repository for Reinforcement Algorithms Home-page: http://github.com/StanfordVL/Surreal Author: Stanford Vision and Learning Lab Author-email: UNKNOWN License: GPLv3 Description-Content-Type: UNKNOWN Keywords: Reinforcement Learning,Deep Learning,Distributed Computing Platform: UNKNOWN Classifier: Development Status :: 2 - Pre-Alpha Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence Classifier: Environment :: Console Classifier: Programming Language :: Python :: 3 Requires-Dist: gym Requires-Dist: robosuite Requires-Dist: mujoco-py (<1.50.2,>=1.50.1) Requires-Dist: tabulate Requires-Dist: tensorflow Requires-Dist: tensorboardX Requires-Dist: imageio Requires-Dist: pygame Requires-Dist: benedict Requires-Dist: nanolog Requires-Dist: psutil Requires-Dist: tabulate Requires-Dist: imageio Requires-Dist: caraml (>=0.10.0) Requires-Dist: symphony (>=0.9.1) Requires-Dist: torchx Requires-Dist: tensorplex Requires-Dist: cloudwise (>=0.1.1) Requires-Dist: Cython (<0.29) `SURREAL `__ ========================================== | `About <#open-source-distributed-reinforcement-learning-framework>`__ | `Installation <#installation>`__ | `Benchmarking <#benchmarking>`__ | `Citation <#citation>`__ Open-Source Distributed Reinforcement Learning Framework -------------------------------------------------------- *Stanford Vision and Learning Lab* `SURREAL `__ is a fully integrated framework that runs state-of-the-art distributed reinforcement learning (RL) algorithms. .. container:: - **Scalability**. RL algorithms are data hungry by nature. Even the simplest Atari games, like Breakout, typically requires up to a billion frames to learn a good solution. To accelerate training significantly, SURREAL parallelizes the environment simulation and learning. The system can easily scale to thousands of CPUs and hundreds of GPUs. - **Flexibility**. SURREAL unifies distributed on-policy and off-policy learning into a single algorithmic formulation. The key is to separate experience generation from learning. Parallel actors generate massive amount of experience data, while a *single, centralized* learner performs model updates. Each actor interacts with the environment independently, which allows them to diversify the exploration for hard long-horizon robotic tasks. They send the experiences to a centralized buffer, which can be instantiated as a FIFO queue for on-policy mode and replay memory for off-policy mode. .. raw:: html - **Reproducibility**. RL algorithms are notoriously hard to reproduce [Henderson et al., 2017], due to multiple sources of variations like algorithm implementation details, library dependencies, and hardware types. We address this by providing an *end-to-end integrated pipeline* that replicates our full cluster hardware and software runtime setup. .. raw:: html Installation ------------ | Surreal algorithms can be deployed at various scales. It can run on a single laptop and solve easier locomotion tasks, or run on hundreds of machines to solve complex manipulation tasks. | \* `Surreal on your Laptop `__ | \* `Surreal on Google Cloud Kubenetes Engine `__ | \* `Customizing Surreal `__ | \* `Documentation Index `__ Benchmarking ------------ - Scalability of Surreal-PPO with up to 1024 actors on Surreal Robotics Suite. |image0| - Training curves of 16 actors on OpenAI Gym tasks for 3 hours, compared to other baselines. Citation -------- Please cite our CORL paper if you use this repository in your publications: :: @inproceedings{corl2018surreal, title={SURREAL: Open-Source Reinforcement Learning Framework and Robot Manipulation Benchmark}, author={Fan, Linxi and Zhu, Yuke and Zhu, Jiren and Liu, Zihua and Zeng, Orien and Gupta, Anchit and Creus-Costa, Joan and Savarese, Silvio and Fei-Fei, Li}, booktitle={Conference on Robot Learning}, year={2018} } .. |image0| image:: .README_images/scalability-robotics.png