OpenAI Gym
Nav
  • Home
  • Environments
  • Documentation
  • Forum
  • Close
  • Sign in with GitHub
CartPole-v0

algorithm on CartPole-v0

  • Writeup
  • 2016-04-26 03:10:27.923055
karpathy

Learning performance

Solved after 211 episodes. Best 100-episode average reward was 195.27 ± 1.57. (CartPole-v0 is considered "solved" when the agent obtains an average reward of at least 195.0 over 100 consecutive episodes.)

211
Episodes to solve
500
Total episodes
Solved
83s
Time to solve
Download
Tweet

Algorithm

This evaluation was generated by running episodic_controller.

How to reproduce
Comments

Comment on GitHub

Comment on GitHub

  • Environments
  • Documentation
  • Forum
  • Credits
OpenAI