All Projects → MLEveryday → 60_days_rl_challenge

MLEveryday / 60_days_rl_challenge

Licence: mit
60_Days_RL_Challenge中文版

Projects that are alternatives of or similar to 60 days rl challenge

Applied Reinforcement Learning
Reinforcement Learning and Decision Making tutorials explained at an intuitive level and with Jupyter Notebooks
Stars: ✭ 229 (+148.91%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Reinforcement Learning
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
Stars: ✭ 3,329 (+3518.48%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Rlai Exercises
Exercise Solutions for Reinforcement Learning: An Introduction [2nd Edition]
Stars: ✭ 97 (+5.43%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Text summurization abstractive methods
Multiple implementations for abstractive text summurization , using google colab
Stars: ✭ 359 (+290.22%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Basic reinforcement learning
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
Stars: ✭ 826 (+797.83%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Machine Learning From Scratch
Succinct Machine Learning algorithm implementations from scratch in Python, solving real-world problems (Notebooks and Book). Examples of Logistic Regression, Linear Regression, Decision Trees, K-means clustering, Sentiment Analysis, Recommender Systems, Neural Networks and Reinforcement Learning.
Stars: ✭ 42 (-54.35%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Gdrl
Grokking Deep Reinforcement Learning
Stars: ✭ 304 (+230.43%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Lagom
lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.
Stars: ✭ 364 (+295.65%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
David Silver Reinforcement Learning
Notes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.
Stars: ✭ 623 (+577.17%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Awesome Ai Books
Some awesome AI related books and pdfs for learning and downloading, also apply some playground models for learning
Stars: ✭ 855 (+829.35%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Notebooks
Some notebooks
Stars: ✭ 53 (-42.39%)
Mutual labels:  artificial-intelligence, jupyter-notebook, reinforcement-learning
Learning2run
Our NIPS 2017: Learning to Run source code
Stars: ✭ 57 (-38.04%)
Mutual labels:  artificial-intelligence, reinforcement-learning
Mlkatas
A series of self-correcting challenges for practicing your Machine Learning and Deep Learning skills
Stars: ✭ 58 (-36.96%)
Mutual labels:  jupyter-notebook, challenge
Data Science Best Resources
Carefully curated resource links for data science in one place
Stars: ✭ 1,104 (+1100%)
Mutual labels:  artificial-intelligence, reinforcement-learning
Rl Workshop
Reinforcement Learning Workshop for Data Science BKK
Stars: ✭ 73 (-20.65%)
Mutual labels:  jupyter-notebook, reinforcement-learning
Evalai
☁️ 🚀 📊 📈 Evaluating state of the art in AI
Stars: ✭ 1,087 (+1081.52%)
Mutual labels:  artificial-intelligence, challenge
Awesome Decision Making Reinforcement Learning
A selection of state-of-the-art research materials on decision making and motion planning.
Stars: ✭ 68 (-26.09%)
Mutual labels:  artificial-intelligence, reinforcement-learning
Rl Course Experiments
Stars: ✭ 73 (-20.65%)
Mutual labels:  jupyter-notebook, reinforcement-learning
Reinforcement Learning
Reinforcement learning material, code and exercises for Udacity Nanodegree programs.
Stars: ✭ 77 (-16.3%)
Mutual labels:  jupyter-notebook, reinforcement-learning
Mathy
Tools for using computer algebra systems to solve math problems step-by-step with reinforcement learning
Stars: ✭ 79 (-14.13%)
Mutual labels:  jupyter-notebook, reinforcement-learning

强化学习60天

英文地址

我为了你我设计这个挑战:在这60天里深入学习“深度强化学习”。

你肯定听说过 Deepmind with AlphaGo ZeroOpenAI in Dota 2 取得的惊人成绩! 你难道不想知道他们是如何工作的吗?现在正是你我最终学会“深度强化学习”,并应用到已有项目的时机。

终极目标是使用这些多功能的技术,并应用他们到各种重要的真实世界问题中。Demis Hassabis

这个项目引导你完成从最基本的到高级的 AlphaGo Zero 深度强化学习算法。你可以发现按周组织的主题建议学习资源。 同时,每周我会提供用Python实现的应用实例,帮助你更好地消化理论。

这是原作者的第一个此类型项目,有任何想法,建议或改进都可以联系作者 [email protected]

在整个挑战期间,作者将持续更新此项目,请保持关注。

MLEveryday 提示:以下资源尽可能换成国内可访问网站,并用标签中文英文字幕英文等区别。如果有找到中文版,请通过issue反馈。

必备知识

  • 了解 Python 和 PyTorch
  • 了解机器学习
  • 了解深度学习(MLP,CNN 和 RNN)

项目(待定)

  • Q-learning
  • DQN
  • AC2
  • ES
  • AlphaGo Zero

第一周 - 强化学习介绍

第二周 - 强化学习基础:马尔可夫决策过程,动态规划与无模型控制

忘记过去的人,终将重蹈覆辙。 - George Santayana

在这一周,我们将会学习基本的强化学习内容,我们将通过评估和优化表示策略和状态的函数去定义现实世界的各类问题。


理论材料


本周项目

Q-learning解决冰冻湖问题. 在本练习中,你将学会使用 SARSA 或者 Q-learning.


想知道更多

第三周 - 值函数近似和DQN(Deep Q-Learning)

本周我们学习更多高级概念,并应用深度神经网络到Q-learning算法中。


理论材料

讲座

论文

必读
DQN 扩展

本周项目

DQN and some variants applied to Pong

本周的目标是开发一个 DQN 算法玩 Atari 游戏。为了使项目更有趣,我开发3个 DQN 变型:Double Q-learningMulti-step learningDueling networksNoisy Nets。使用它们玩游戏,如果你有信心,你可以实现 Prioritized replay, Dueling networks 或者 Distributional RL。 阅读论文去了解更多改进。


建议

Week 4 - A2C and A3C

Week 5 - RL in continous space - TRPO/PPO

Week 6 - Evolution Strategies and Genetic Algorithms

Week 7 - I2A

Week 8 - AlphaGoZero + Bonus

Last 4 days - Review + sharing

强化学习论文

强化学习资源

📺 英文|youtubeDeep Reinforcement Learning - UC Berkeley class by Levine, check here their site.

📺 英文|youtubeReinforcement Learning course - by David Silver, DeepMind. Great introductory lectures by Silver, a lead researcher on AlphaGo. They follow the book Reinforcement Learning by Sutton & Barto.

📓 Reinforcement Learning: An Introduction - by Sutton & Barto. The "Bible" of reinforcement learning. Here you can find the PDF draft of the second version.

额外的资源

📚 Awesome Reinforcement Learning. 强化学习专用资源列表

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].