- 博客(30)
- 资源 (8)
- 问答 (2)
- 收藏
- 关注
原创 Installing mujoco-py v1.5 on windows10
This post is based on instructions here.Step 1: get a mjkeyThe first thing is to acquire a mujoco key.Go to this site. Fill in the blanks. There are several user types:trial allows you one month ...
2019-06-24 14:30:56 1241
原创 frequently used linux commands
find out the pid that occupies certain portps aux | grep <port>netstat -anp | grep <port>find out the run file locationwhich <cmd>e.g.
2019-01-18 12:46:30 143
原创 Enable Math with your Kramdown or Jekyll blog
To enable Latex math, you need to first enable Mathjax.This answer gives a solution by adding js.<script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AM...
2019-01-08 17:35:14 181
原创 [bug] Retrying fetcher due to error (2/4): Bundler::Fetcher::CertificateFailureError
when bundle install errors occur like:Fetching source index from https://rubygems.org/Retrying fetcher due to error (2/4): Bundler::Fetcher::CertificateFailureError Could not verify the SSL certifi...
2019-01-07 11:47:19 3061
原创 [bug] Liquid Exception: incompatible character encodings: GBK and UTF-8 in /_layouts/default.html
Liquid Exception: incompatible character encodings: GBK and UTF-8 in /_layouts/default.htmlI encountered this error when setting up my Jekyll site.According to this post, I modified the file [\the\i...
2019-01-07 01:08:35 794 1
原创 [CS294-112] model-based RL
Control and PlanningOpen-loop Trajectory optimization methodsassumptions: a (learned) dynamics model in handobjective: find the optimal action sequence that maximizes the expected return of the tra...
2018-12-28 18:19:54 1318 1
原创 [cs294-112 notes] lecture 6 actor-critic
p4recapping policy gradients.the gradient is computed on a sampling estimate of the original objective. The estimate is averaged across n trajectories and each T time steps.‘reward to go’ is the su...
2018-12-12 16:09:32 176
原创 Learning to Adapt: Meta-Learning for Model-Based Control
sudden changes in environment cause failureif encounter pertub in past experience, can in pri. learn to adaptstudy model-based online adaptationsample efficient than model-freealleviate a challeng...
2018-12-11 01:02:25 657
原创 One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
IntroductionThe goal is to : enable a robot to learn from one raw video of human demonstrations on a new task, with the help of the prior knowledge of some old tasks, where both human demonstrations ...
2018-12-11 00:43:25 467
原创 [ipython] install ipykernel in multiple environments 多conda环境安装使用ipython
refer to this link.I have multiple environments in anaconda, but ipython breaks and often casts module not found exception.I had thought this is solved in this, but clearly it is not. python -m ipyk...
2018-12-03 09:56:17 675 1
原创 One-Shot Visual Imitation Learning via Meta-Learning
IntroductionThe goal of this work is to enable a robotic generalist to only learn from very few demonstrations, which may even be raw videos. This problem setting instantly brings us into the setting...
2018-11-25 20:14:07 877 3
原创 Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
motivationModel-based approaches enjoys 1) sample efficiency (meaning they learn quickly), 2) and a reward-independent dynamics model (thinking of model-free approaches require the reward function to...
2018-11-24 17:27:02 672
原创 Robust Adversarial Reinforcement Learning
motivationCurrent RL methods fail to generalize due to two issues:test generalizationdata is scarce especially in the sense of real-world data. So RL models often overfit to the training scenarios...
2018-11-24 02:46:37 1139
原创 [OpenAI SpinningUp] Key Concepts and Terminology
Key Concepts and Terminologyoverviewagent, environment, reward, returnstates and observationsstateob.representationsdifferencein practiceaction spacesdiscretecontinuousrepresentationswhy ...
2018-11-21 14:30:42 197
原创 [logging] How to log into console and file simultaneously? 同时log到控制台和文件
I follow this guide and learned quite a bit.Briefly speaking, to direct prompts to several destinations simultaneously requires the use of handlers. A handler is bound to one stream, and can be set l...
2018-11-18 21:08:00 208
原创 [sklearn] 'error, no feasible solution' when calling scipy's minimize function
I was using L-BFGS-B the bounded optimization method in scipy.optimize.minimize, but the returned OptimizeResult object kept telling me its failure. res.message notifies ‘error, no feasible solution’....
2018-11-18 01:38:33 496
原创 [jupyter] Jupyter cannot load installed package Jupyter报错‘No module named ..’,但已经安装
I am using anaconda3 and pip install a package ‘BayesianOptimization’.I confirmed the installation of the package by conda list Bayes,however Jupyter Notebook just couldn’t find it.According to this...
2018-11-18 01:27:24 1358
原创 [tensorflow] reproduce in tensorflow: tf.set_random_seed() Tensorflow中复现实验
There are two types of seeding in tensorflow:graph-leveltypically by calling tf.set_random_seed(seed)op-levelby setting the seed= param in the tf.random functions.What are the differences?gra...
2018-11-14 16:14:32 277
原创 [anaconda] frequently used conda commands
conda create python=3.6 -n your_env_nameconda listconda list some_packageconda install some_packageconda update some_packageconda remove some_packageconda clean -aconda env listconda env remo...
2018-11-08 00:56:45 136
原创 [tensorflow] How to subsample dataset like bootstrapping using tf.data API? Tensorflow怎么对数据集做采样
The problem is I have big dataset and for each epoch i want to use only random subset of this dataset, but how can I make it using tf.data API.There are two approaches.use filtersdef create_filte...
2018-11-08 00:49:51 486
原创 [bug] ExecutableNotFound: failed to execute ['dot', '-Tsvg'], make sure the Graphviz executables are
when calling sklearn.tree.export.export_graphviz() I encountered this error:---------------------------------------------------------------------------FileNotFoundError Trace...
2018-11-04 18:45:05 1844
原创 [bug] "TypeError: read_feather() got an unexpected keyword argument 'nthreads'"
when running this cellpd.read_feather('tmp/bulldozers-raw')I got this error:---------------------------------------------------------------------------TypeError Tr...
2018-11-04 17:39:15 2378
原创 [bug] Jupyter Notebook Kernel Error
Traceback (most recent call last): File "E:\Anaconda3\envs\fastai\lib\site-packages\tornado\web.py", line 1512, in _execute result = yield result File "E:\Anaconda3\envs\fastai\li...
2018-10-31 21:58:26 256
原创 [Fastai] How to set up fastai library on windows 10? Windows 10如何安装fastai库
According to Jeremy’s post: (assume you have gpu with cuda, conda and git installed)clone the git repogit clone https://github.com/fastai/fastai.gitopen your anaconda prompt and set up the cond...
2018-10-31 21:53:40 1285
原创 [Fastai] ML lecture1 note
Bookspython for data analysis, 2nd editionintroduction to machine learning with pythonPython Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edi...
2018-10-30 22:33:01 343
原创 [Tensorflow] 如何从pb文件生成标准的tensorflow checkpoint文件?
How to generate a tensorflow checkpoint file given a pb file?
2018-10-30 19:59:28 2114
原创 [python] 从python2.x迁移到python3.x的常见操作
print 'something' > print('something')xrange() > range()除法divisionpython 2.x : 整数 / 整数python 3.x : 整数 // 整数这个很难发现,因为python弱类型。python2.x中/是classic division,和C++一样,所以两个整数操作数会有整数结果,特别是可以自动取整...
2018-10-16 16:35:37 368
原创 [Tensorflow] 统计模型的参数数量 How to calculate the amount of parameters in my model?
import logginglogging.basicConfig(level=logging.INFO, format='%(message)s', filemode='w', filename=config.logger)def _params_usage(): total = 0 prompt = [] for v in tf.trainable_variables(): s...
2018-10-16 16:10:49 2175
原创 [tensorflow] 如何从pb模型文件中获得参数信息 How to obtain parameters information from a tensorflow .pb file?
因为要和SOTA比较模型的复杂度,我想知道参数数量。但是模型文件不是tensorflow checkpoint,而是pb文件,我发现当导入graph后,tf.trainable_variables()返回空。Problem setting : I need to compare with state-of-the-arts the model complexity so the model pa...
2018-10-16 12:12:47 3074
原创 “error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools"
“error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools": http://landinghub.visualstudio.com/visual-cpp-build-tools”安装lws报了这个错,python3.5,意思是要安装vc14,但是我没有vs2015,给的...
2018-10-03 14:09:38 998 1
[全] learning from data+e-chapters 机器学习基石/技法(林轩田)textbook
2017-08-26
ippicv_linux_20151201.tgz
2017-08-17
Android编程权威指南pdf(非扫描版不失真)+源代码
2016-07-31
Android编程权威指南第二版(android programming the big nerd ranch edition 2) 源代码
2016-07-30
Spring mvc 如何实现带参数跳转到外部网站页面
2017-03-03
初学C……求助float有效数字的问题
2015-08-29
TA创建的收藏夹 TA关注的收藏夹
TA关注的人