Kory korymath

## gist:a1aafd41faeb92b1a20784e292b2c48e
Following https://github.com/rllab/rllab

## gist:26a68fd8ac32b0dcc56fb9af84bb32e6
Using TRPO from https://github.com/rllab/rllab

## gist:6880c0237b552b3d851937127e4133a4
Using the rllab TRPO algorithm

## gist:1a2f31b9f47f042d62135e8e1796916f
"""
Policy Gradients
1. Sample paths.
2. Process paths (compute advantage, baseline, rewards, etc)
3. Run the paths through the policy (function approximator)
4. Compute gradients/update policy model weights
5. Profit?!?!
How we optimize the policy
--------------------------
L(theta) = sum t=0 to T-1 log policy(action_t | state_t, theta) * A_t

## init.lua
hs.hotkey.bind({"cmd", "alt", "ctrl"}, "Left", function()
  local win = hs.window.focusedWindow()
  local f = win:frame()
  local screen = win:screen()
  local max = screen:frame()

  f.x = max.x
  f.y = max.y
  f.w = max.w / 2
  f.h = max.h

## shakespear_sonnet.txt
SONNETS


TO THE ONLY BEGETTER OF
THESE INSUING SONNETS
MR. W. H. ALL HAPPINESS
AND THAT ETERNITY
PROMISED BY
OUR EVER-LIVING POET WISHETH

## sarsa-lambda.py
"""
Translated from https://webdocs.cs.ualberta.ca/~sutton/MountainCar/MountainCar1.cp
Algorithm described at https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node89.html
Some minor adjustments to constants were made to make the program work on environments
besides Mountain Car.
"""

import random
import math
import numpy as np

## nips-accepted-papers.py
from sklearn.feature_extraction.text import CountVectorizer
from collections import Counter
import numpy as np

with open('accepted-papers.txt', 'r') as myfile:
	data=myfile.read().replace('\n', '')

lectures = data
bigram_vectorizer = CountVectorizer(ngram_range=(2, 10), stop_words='english')
analyze = bigram_vectorizer.build_analyzer()

## torch-twrl policy gradient
Following the installation and first test for torch-twrl
https://github.com/twitter/torch-twrl

Run code:
cd examples
chmod u+x cartpole-pg.sh
./cartpole-pg.sh

## gist:38c0d88e021f8e9f13e231fc637f125f
https://krb-sjobs.brassring.com/TGnewUI/Search/home/HomeWithPreLoad?PageType=JobDetails&jobid=74414&partnerid=26059&siteid=5016&type=mail
	"""
	Policy Gradients
	1. Sample paths.
	2. Process paths (compute advantage, baseline, rewards, etc)
	3. Run the paths through the policy (function approximator)
	4. Compute gradients/update policy model weights
	5. Profit?!?!
	How we optimize the policy
	--------------------------
	L(theta) = sum t=0 to T-1 log policy(action_t \| state_t, theta) * A_t
	hs.hotkey.bind({"cmd", "alt", "ctrl"}, "Left", function()
	local win = hs.window.focusedWindow()
	local f = win:frame()
	local screen = win:screen()
	local max = screen:frame()

	f.x = max.x
	f.y = max.y
	f.w = max.w / 2
	f.h = max.h
	SONNETS



	TO THE ONLY BEGETTER OF
	THESE INSUING SONNETS
	MR. W. H. ALL HAPPINESS
	AND THAT ETERNITY
	PROMISED BY
	OUR EVER-LIVING POET WISHETH
	"""
	Translated from https://webdocs.cs.ualberta.ca/~sutton/MountainCar/MountainCar1.cp
	Algorithm described at https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node89.html
	Some minor adjustments to constants were made to make the program work on environments
	besides Mountain Car.
	"""

	import random
	import math
	import numpy as np
	from sklearn.feature_extraction.text import CountVectorizer
	from collections import Counter
	import numpy as np

	with open('accepted-papers.txt', 'r') as myfile:
	data=myfile.read().replace('\n', '')

	lectures = data
	bigram_vectorizer = CountVectorizer(ngram_range=(2, 10), stop_words='english')
	analyze = bigram_vectorizer.build_analyzer()
	Following the installation and first test for torch-twrl
	https://github.com/twitter/torch-twrl

	Run code:
	cd examples
	chmod u+x cartpole-pg.sh
	./cartpole-pg.sh