Patrick Haluptzok haluptzok

Research Engineer in AI working on extending LLMs to do more complicated tasks and solve problems that require reasoning, like writing code!

haluptzok / pg-pong.py

Last active February 2, 2024 15:40 — 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 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