Kumar Ishan kumarishan

Code used to obtain these results can be found at the url https://github.com/joschu/modular_rl, commit 50cdfdf375e69d86e3db6eb2ad0218ea6aebf371. The command line expression used for all the environments can be found in the text file below. Note that the same exact parameters and policies were used for all tasks, except for timesteps_per_batch, which was varied based on the difficulty of the task. The important parameters are:

gamma=0.995: discount
lam=0.97: see GAE paper for explanation
agent=TrpoAgent: name of the class, which specifies policy and value function architecture. In this case, we used two hidden layers of size 64, with tanh activations
cg_damping: multiple of the identity added for conjugate gradient

This re-styles your sublime text sidebar to be dark, it fits default Monokai theme.

Save the Default.sublime-theme file into packages/Theme - Default, make a backup of your original if you want to be able to go back easily.

Based on:

	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)

	import scala.reflect.runtime.universe.TypeTag
	import scala.annotation.implicitNotFound

	@implicitNotFound("Sorry, type inference was unable to figure out the type. You need to provide it explicitly.")
	trait NotNothing[T]

	object NotNothing {
	private val evidence: NotNothing[Any] = new Object with NotNothing[Any]

	implicit def notNothingEvidence[T](implicit n: T =:= T): NotNothing[T] =

	echo 'export PATH=$HOME/local/bin:$PATH' >> ~/.bashrc
	. ~/.bashrc
	mkdir ~/local
	mkdir ~/node-latest-install
	cd ~/node-latest-install
	curl http://nodejs.org/dist/node-latest.tar.gz \| tar xz --strip-components=1
	./configure --prefix=~/local
	make install # ok, fine, this step probably takes more than 30 seconds...
	curl https://www.npmjs.org/install.sh \| sh