Python强化学习实战,Anaconda公司的高级数据科学家讲解

【导读】Christine Doig是Anaconda公司的高级数据科学家。没错Anaconda就是那个著名的Python科学计算与发行管理软件。Christine Doig从最基本的强化学习概念开始介绍强化学习Python实践经验,并以强化学习中的经典任务--Cartpole问题作为学习的入门例子,讲解从环境搭建、模型训练再到最后的效果评估的结果。

▌简介

Cartpole描述的问题可以认为是:在一辆小车上竖立一根杆子,然后给小车一个推或者拉的力,使得杆子尽量保持平衡不滑倒。

更详细的描述可参见openai官网上关于Cartpole问题的解释:https://gym.openai.com/envs/CartPole-v0

▌强化学习用到的python库

OpenAI

Gym: Toolkit for developing and comparing reinforcement learningalgorithms. MIT License, Last commit: November 2017

baselines: high-quality implementations of reinforcement learning algorithms,MIT License, Last commit: November 2017

TensorForce, A TensorFlow library for applied reinforcement learning, Apache 2,Last commit: November 2017

DeepRL, Highly modularized implementation of popular deep RL algorithms byPyTorch, Apache 2 License, Last commit: November 2017

RLlab, a framework for developing and evaluating reinforcement learningalgorithms, MIT License, Last commit: July 2017

AgentNet, Python library for deep reinforcement learning usingTheano+Lasagne, MIT License, Last commit: August 2017

RLPy, the Reinforcement Learning Library for Education and Research,3-Clause BSD License, Last commit: April 2016.

PyBrain, the Python Machine Learning Library, 3-Clause BSD License, Lastcommit: March 2016.

▌强化学习资源

Reinforcement Learning courseby David Silver

http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html

https://blog.acolyer.org/2017/11/17/mastering-the-game-of-go-without-humanknowledge/

https://keon.io/deep-q-learning/

https://rishav1.github.io/reinlearning/2017/01/05/simple-swarm-intelligenceoptimization-for-cartpole-balancing-problem.html

AlphaGo Zero's win, what itmeans, Fast Forward Labs: http:// blog.fastforwardlabs.com/2017/10/25/alphago-zero.html

更多可以查看专知以前推出的强化学习荟萃资料:

▌PPT内容

参考链接:

https://speakerdeck.com/chdoig/rl-pytexas-2017

  • 发表于:
  • 原文链接:http://kuaibao.qq.com/s/20171211G00PTL00?refer=cp_1026

扫码关注云+社区