Skip to content

Instantly share code, notes, and snippets.

View hunkim's full-sized avatar
:bowtie:
Happy!

Sung Kim hunkim

:bowtie:
Happy!
View GitHub Profile
# Borrowed from NAF. Might be plugged into DeepSets.
class SigmoidFlow(nn.Module):
def __init__(self,K):
super().__init__()
self.W = nn.Parameter(torch.FloatTensor(K,1))
self.b = nn.Parameter(torch.FloatTensor(1,K))
self.alpha = nn.Linear(1,K)
def forward(self,x):
@arturbekasov
arturbekasov / nips2017-arxiv-papers.md
Last active December 1, 2017 20:02
NIPS2017 papers which have [easy-to-find] arXiv preprints
@kylemcdonald
kylemcdonald / pytorch+char-rnn.ipynb
Last active June 12, 2020 21:34
Recreating char-rnn from the spro/practical-pytorch tutorials.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@karpathy
karpathy / pg-pong.py
Created May 30, 2016 22:50
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym
# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward