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

CartPole-v0

A pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The system is controlled by applying a force of +1 or -1 to the cart. The pendulum starts upright, and the goal is to prevent it from falling over. A reward of +1 is provided for every timestep that the pole remains upright. The episode ends when the pole is more than 15 degrees from vertical, or the cart moves more than 2.4 units from the center.

CartPole-v0 defines "solving" as getting average reward of 195.0 over 100 consecutive trials.

This environment corresponds to the version of the cart-pole problem described by Barto, Sutton, and Anderson [Barto83].

karpathy's algorithm, Took 211 episodes to solve the environment. 195.27 ± 1.57 2016-04-26 03:10:27.923055

CartPole-v0 Evaluations

Algorithm Episodes before solve Submitted
n1try's algorithm writeup 85.0 2017-09-11 05:40:20.490911
mbalunovic's algorithm writeup 306.0 2017-09-11 06:38:13.848282
ruippeixotog's algorithm writeup 933.0 2017-09-10 00:41:30.294576
ruippeixotog's algorithm writeup 961.0 2017-09-09 20:31:56.952075
barbossusus's algorithm 0.0 2017-09-10 18:17:21.685298
DaveLeongSingapore's algorithm 0.0 2017-09-10 11:38:08.628986
guillermo-sanchez's algorithm 0.0 2017-09-10 08:04:50.122232
jiexunsee's algorithm 13.0 2017-09-10 22:19:34.547808
haron1100's algorithm 36.0 2017-09-11 01:51:03.572226
gengshg's algorithm 59.0 2017-09-11 03:28:15.250687
gengshg's algorithm 59.0 2017-09-11 03:20:56.875442
gengshg's algorithm 59.0 2017-09-11 03:13:49.406095
gengshg's algorithm 59.0 2017-09-11 01:47:28.512624
gengshg's algorithm 61.0 2017-09-11 02:08:00.552606
haron1100's algorithm 88.0 2017-09-10 17:36:40.197322
lyebi's algorithm 100.0 2017-09-10 12:19:26.419041
KuribohG's algorithm 129.0 2017-09-14 07:49:52.072128
CallumQuin's algorithm 137.0 2017-09-10 09:30:31.506820
KuribohG's algorithm 138.0 2017-09-10 02:32:47.526664
hzwer's algorithm 177.0 2017-09-11 05:24:25.822706
hzwer's algorithm 189.0 2017-09-10 10:11:02.542472
sonic1sonic's algorithm 205.0 2017-09-10 14:43:28.960811
sonic1sonic's algorithm 226.0 2017-09-10 06:44:26.458592
hzwer's algorithm 247.0 2017-09-10 03:08:18.861701
hzwer's algorithm 248.0 2017-09-10 17:53:29.211376
sonic1sonic's algorithm 357.0 2017-09-10 14:25:16.146465
CallumQuin's algorithm 373.0 2017-09-11 09:39:40.939878
hzwer's algorithm 457.0 2017-09-10 14:53:50.214188
hzwer's algorithm 501.0 2017-09-10 15:16:35.603489
jing582's algorithm 557.0 2017-09-10 21:46:00.326572
KuribohG's algorithm 647.0 2017-09-10 02:07:32.036057
hzwer's algorithm 649.0 2017-09-10 09:13:54.216810
sonic1sonic's algorithm 675.0 2017-09-10 07:28:27.196029
hzwer's algorithm 696.0 2017-09-10 02:41:54.011887
hzwer's algorithm 798.0 2017-09-10 02:18:00.334680
sonic1sonic's algorithm 817.0 2017-09-10 07:14:11.955434
hzwer's algorithm 824.0 2017-09-10 16:36:04.102578
hzwer's algorithm 827.0 2017-09-10 02:56:41.234184
hzwer's algorithm 862.0 2017-09-10 02:03:05.467694
LyubomyrD's algorithm 934.0 2017-09-14 20:36:16.395393
hzwer's algorithm 962.0 2017-09-10 02:31:03.376238
TangerineMing's algorithm 1059.0 2017-09-10 02:20:56.918047
hzwer's algorithm 1189.0 2017-09-10 01:44:33.964550
hzwer's algorithm 1488.0 2017-09-09 14:53:20.750520
hzwer's algorithm 1773.0 2017-09-09 18:12:37.242591
hzwer's algorithm 1894.0 2017-09-10 15:51:02.713221
KuribohG's algorithm N/A 2017-09-14 08:08:46.228867
hzwer's algorithm N/A 2017-09-12 06:11:25.371019
hzwer's algorithm N/A 2017-09-12 06:11:00.520968
hzwer's algorithm N/A 2017-09-12 05:48:08.525162
Ema93sh's algorithm N/A 2017-09-11 14:50:13.392481
Ema93sh's algorithm N/A 2017-09-11 07:31:48.046570
Ema93sh's algorithm N/A 2017-09-11 07:30:46.765827
Ema93sh's algorithm N/A 2017-09-11 07:05:35.779928
hzwer's algorithm N/A 2017-09-11 05:36:28.506050
sanshin5050's algorithm N/A 2017-09-11 04:42:24.493166
gengshg's algorithm N/A 2017-09-11 03:03:30.442585
Ema93sh's algorithm N/A 2017-09-11 00:19:22.841566
Ema93sh's algorithm N/A 2017-09-11 00:14:55.430601
jing582's algorithm N/A 2017-09-10 21:40:43.642979
hzwer's algorithm N/A 2017-09-10 16:03:54.818583
hzwer's algorithm N/A 2017-09-10 15:35:22.867469
hyyperion's algorithm N/A 2017-09-10 14:10:52.786218
hyyperion's algorithm N/A 2017-09-10 13:59:39.614600
hzwer's algorithm N/A 2017-09-10 13:54:09.111053
hzwer's algorithm N/A 2017-09-10 12:37:21.722768
lyebi's algorithm N/A 2017-09-10 11:47:17.526830
lyebi's algorithm N/A 2017-09-10 11:39:53.986585
lyebi's algorithm N/A 2017-09-10 11:37:45.483654
lyebi's algorithm N/A 2017-09-10 11:36:43.869114
hzwer's algorithm N/A 2017-09-10 10:22:55.872736
zhiyong1997's algorithm N/A 2017-09-10 07:29:12.188330
kawaiisampler's algorithm N/A 2017-09-10 05:40:00.672686
hzwer's algorithm N/A 2017-09-10 04:05:48.830809
hzwer's algorithm N/A 2017-09-10 03:56:42.223013
wxl18039675170's algorithm N/A 2017-09-10 03:20:07.066602
KuribohG's algorithm N/A 2017-09-10 02:00:27.630647
KuribohG's algorithm N/A 2017-09-10 01:52:41.731399
hzwer's algorithm N/A 2017-09-10 01:48:29.690719
KuribohG's algorithm N/A 2017-09-10 01:37:43.578920
KuribohG's algorithm N/A 2017-09-10 00:48:27.666578
KuribohG's algorithm N/A 2017-09-10 00:40:08.317606
KuribohG's algorithm N/A 2017-09-10 00:34:30.996335
KuribohG's algorithm N/A 2017-09-10 00:32:30.525282
ruippeixotog's algorithm N/A 2017-09-09 20:13:48.370702
ruippeixotog's algorithm N/A 2017-09-09 20:00:51.081041
bastigw's algorithm N/A 2017-09-09 18:00:15.650573
bastigw's algorithm N/A 2017-09-09 17:55:35.551017
fiasco-zh's algorithm N/A 2017-09-09 17:13:36.788108
KuribohG's algorithm N/A 2017-09-09 17:01:48.254657
hzwer's algorithm N/A 2017-09-09 16:47:35.389967
hzwer's algorithm N/A 2017-09-09 16:05:27.603509
hzwer's algorithm N/A 2017-09-09 15:31:43.086169
KuribohG's algorithm N/A 2017-09-09 15:20:57.814585
KuribohG's algorithm N/A 2017-09-09 15:15:51.120990
KuribohG's algorithm N/A 2017-09-09 15:08:53.440398
hzwer's algorithm N/A 2017-09-09 15:06:52.402564
KuribohG's algorithm N/A 2017-09-09 15:04:06.498570
KuribohG's algorithm N/A 2017-09-09 14:51:39.246517
Peter0905's algorithm N/A 2017-09-09 14:48:17.002306
[Barto83]AG Barto, RS Sutton and CW Anderson, "Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problem", IEEE Transactions on Systems, Man, and Cybernetics, 1983.
  • Environments
  • Documentation
  • Forum
  • Credits
OpenAI