Qiushi Pan qqpann

mujoco_py のマーカーの使い方

この記事は強化学習 Advent Calendar 2021の12/22の記事です。

はじめまして！東京大学の吉田です。

大学では身体を持って自律的に発達する人工知能をつくることに興味があって、それを研究しています。

今回の記事は強化学習というよりは強化学習の環境をmujoco-pyを使って作るときのtipsといった内容です。すでに強化学習の環境を作ってみたり、mujoco-pyを使ってMujocoをつかった物理シミュレーションをしている・やろうとしている人向けの内容です。

https://github.com/James-Yu/LaTeX-Workshop/wiki/Compile に書いてあったbibのコンパイルを日本語に対応．

VSCodeやLatexをインストールしてなければインストール（https://code.visualstudio.com/）
Latex-Workshopをインストール(https://marketplace.visualstudio.com/items?itemName=James-Yu.latex-workshop)
settings.json(Windows: ファイル > 基本設定 > 設定 or Ctrl + ,， Mac: Code > 基本設定 > 設定 or ⌘ + ,)の{ }内に以下を追加(設定ファイルの変更方法: https://qiita.com/y-w/items/614843b259c04bb91495)

    "latex-workshop.latex.tools": [
        {
            "command": "ptex2pdf",
            "args": [

	const axios = require('axios')
	const decode = require('decode-html')
	const CHANNEL = '#dev'
	const ISSUE_REPO = 'foo/bar'

	exports.otochan = (req, res) => {
	console.log('Received request:', req.body)

	// slack challenge
	if (req.body.challenge) {

	import torch
	from torch import LongTensor
	from torch.nn import Embedding, LSTM
	from torch.autograd import Variable
	from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

	## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
	#
	# Step 1: Construct Vocabulary
	# Step 2: Load indexed data (list of instances, where each instance is list of character indices)

	/* Customize website's scrollbar like Mac OS
	Not supports in Firefox and IE */

	/* total width */
	body::-webkit-scrollbar {
	background-color: #fff;
	width: 16px;
	}

	/* background of the scrollbar except button or resizer */

	{
	/*
	// Place your snippets for C++ here. Each snippet is defined under a snippet name and has a prefix, body and
	// description. The prefix is what is used to trigger the snippet and the body will be expanded and inserted. Possible variables are:
	// $1, $2 for tab stops, ${id} and ${id:label} and ${1:label} for variables. Variables with the same id are connected.
	// Example:
	"Print to console": {
	"prefix": "log",
	"body": [
	"console.log('$1');",

	## Forked from https://gist.github.com/dersam/0ec781e8fe552521945671870344147b
	## Also received help from https://twitter.com/gitkraken/status/691675309725368321

	## Open GitKraken using the current repo directory.
	## This code is for fish shell. The same thing can be done in bash
	## by creating an alias with the command below.

	## `1>/dev/null` directs logs from the terminal
	## `&` allows use of the same terminal instance to do other things

	# Copyright (c) 2016-2018 Ming Qin (覃明) <https://github.com/QinMing>
	# Open source under MIT LICENSE.

	lazy_load() {
	# Act as a stub to another shell function/command. When first run, it will load the actual function/command then execute it.
	# E.g. This made my zsh load 0.8 seconds faster by loading `nvm` when "nvm", "npm" or "node" is used for the first time
	# $1: space separated list of alias to release after the first load
	# $2: file to source
	# $3: name of the command to run after it's loaded
	# $4+: argv to be passed to $3