Skip to content

Instantly share code, notes, and snippets.

View DamienAllonsius's full-sized avatar
🤓

Damien Allonsius DamienAllonsius

🤓
View GitHub Profile
@DamienAllonsius
DamienAllonsius / tetris.py
Created March 7, 2022 14:32 — forked from silvasur/tetris.py
Tetris implementation in Python
#!/usr/bin/env python3
#-*- coding: utf-8 -*-
# Very simple tetris implementation
#
# Control keys:
# Down - Drop stone faster
# Left/Right - Move stone
# Up - Rotate Stone clockwise
# Escape - Quit game
import numpy as np
from matplotlib.pyplot import plot
N = 1000
x_p = np.random.rand(N)
y_p = np.random.rand(N)
p = zip(x_p, y_p)
x_m = -np.random.rand(N)
@DamienAllonsius
DamienAllonsius / pg-pong.py
Created May 10, 2019 15:54 — forked from karpathy/pg-pong.py
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
@DamienAllonsius
DamienAllonsius / gist:aafbddaf5f6b12bb9ff54a274bfa4edc
Last active February 19, 2019 17:28
Reinforcement Learning - Wrapper for downsampling images with Gym Environments. The resulting image is blurred/downsampled by taking the average colors of pixels in rectangle zones.
import gym
import numpy as np
import time
import cv2
from gym.envs.classic_control import rendering
class ObservationZoneWrapper(gym.ObservationWrapper):
def __init__(self, env, downsampled_size_x, downsampled_size_y, blurred, number_gray_colors=0):