Jakub Šlambora Pocuston

Pocuston / Cartpole-v0.py

Last active May 10, 2021 02:25

Solution of Open AI gym environment "Cartpole-v0" (https://gym.openai.com/envs/CartPole-v0) using DQN and Pytorch. It is is slightly modified version of Pytorch DQN tutorial from http://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html. For results see: https://gym.openai.com/evaluations/eval_KYrmuUX4TWGOWYsJl8i6Kg.

	# Solution of Open AI gym environment "Cartpole-v0" (https://gym.openai.com/envs/CartPole-v0) using DQN and Pytorch.
	# It is is slightly modified version of Pytorch DQN tutorial from
	# http://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html.
	# The main difference is that it does not take rendered screen as input but it simply uses observation values from the \
	# environment.

	import gym
	from gym import wrappers
	import random
	import math

Pocuston / Cartpole-v0.py

Created September 3, 2017 15:51

Cartpole-v0 using Pytorch and DQN

	# Solution of Open AI gym environment "Cartpole-v0" (https://gym.openai.com/envs/CartPole-v0) using DQN and Pytorch.
	# It is is slightly modified version of Pytorch DQN tutorial from
	# http://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html.
	# The main difference is that it does not take rendered screen as input but it simply uses observation values from the \
	# environment.

	import gym
	from gym import wrappers
	import random
	import math