Stack Overflow
Stack Overflow

Questions tagged [openai-gym]

OpenAI Gym is a platform for reinforcement learning research that aims to provide a general-intelligence benchmark with a wide variety of environments.

1033 questions
0
votes
1 answer

OpenAI Gym stepping in an externally controlled environment

I have a simulation that ticks the time every 5 seconds. I want to use OpenAI and its baselines algorithms to perform learning in this environment. For that I'd like to adapt the simulation by writing some adapter code that corresponds to the OpenAI…
pascalwhoop
  • 2,984
  • 3
  • 26
  • 40
0
votes
0 answers

Can't run openAI Gym atari with Windows 10

I'm stuck, I've seen a post of Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels of Kapathy, and I copy all code in there and well done, but only have one problem. The result is run fine without gameplay of pong…
LucDaoDaiNhan
  • 1
  • 1
0
votes
0 answers

cannot run the sklearn machine learning model

I am trying to use the sklearn to build a machine learning model for the lunar lander. I use Grid search to tune the model and use joblib to persist the model. enter image description here here is the code: from sklearn.externals import…
HungryBird
  • 1,077
  • 1
  • 11
  • 28
0
votes
1 answer

PPO Update Schedule in OpenAi Baselines Implementations

I'm trying to read through the PPO1 code in OpenAi's Baselines implementation of RL algorithms (https://github.com/openai/baselines) to gain a better understanding as to how PPO works, how one might go about implementing it, etc. I'm confused as to…
ashboy64
  • 83
  • 3
  • 13
0
votes
1 answer

Getting "No standard config is available" when running Openai "gym retro"

I am getting the "NoSuchConfigException: No standard config is available" from pyglet when running Openai "gym retro" on Google colaboratory, running xvfb as the x server.
user650585
  • 313
  • 2
  • 3
  • 10
0
votes
1 answer

Experience Replay is making my agent worse

I have 'successfully' set up a Q-network for solving the 'FrozenLake-v0' env of the OpenAI gym (at least, I think.. not 100% sure how I score - I get 70 to 80 out of 100 successful episodes after 5k episodes of training without Experience Replay).…
Floris
  • 653
  • 4
  • 10
0
votes
1 answer

How to estimate average Q-value per episode?

I'm working on several variants of DQN algoritms and I want to compare their learning efficiecy. I've seen couple graphs showing average Q-value per episode in some github repositories. I'm confused because neural network gives me Q-value for each…
Petr Buchal
  • 53
  • 9
0
votes
1 answer

Python launcher not responding after closing VNC (mac)

I'm trying to create a simple program using universe by openai but every time I close the VNC, the python launcher doesn't respond anymore and I have to force quit it. What can I do to solve this? Thanks
Leonardo Barazza
  • 375
  • 2
  • 10
0
votes
1 answer

Reinforcement Learning - How to we decide the reward to the agent when the input to the game is only pixels?

I am new to RL and the best I've done is CartPole in openAI gym. In cartPole, the API automatically provides the reward given the action taken. How am I supposed to decide the reward when all I have is pixel data and no "magic function" that could…
ParmuTownley
  • 957
  • 2
  • 14
  • 34
0
votes
1 answer

What is meaning of _ in python

While taking outputs from step function of openAI gym environment _ used as the fourth variable.Is it to just for the values which we don't want to use? is there any kind of advantage for using _ instead of any other name? import gym env =…
Yograj Singh Mandloi
  • 553
  • 1
  • 4
  • 16
0
votes
0 answers

How can Making video from MountainCar's reaching goals many times (>1000) reasonably fast

I want to make a video from MountainCar reaching goal (flag position>.5) many times. I am using openai's MountainCar-v0 (with changes in steps and reward limit) but it takes a lot of time to reach the goal. I am using the following code: import…
user3111496
0
votes
1 answer

tflearn creating multiple models

I am working on a machine-learning script with tflearn and gym. I am able to get one network working in my python-script but whenever I try to call my functions to build up a 2nd or 3rd network and train it with model.fit, I get a…
Niclas Eich
  • 11
  • 2
0
votes
1 answer

Invalid moves in reinforcement learning

I have implemented a custom openai gym environment for a game similar to http://curvefever.io/, but with discreet actions instead of continuous. So my agent can in each step go in one of four directions, left/up/right/down. However one of these…
ericwenn
  • 106
  • 1
  • 10
0
votes
1 answer

Feeding a tensorflow placeholder from an array

I'm trying to train CatPole-v0 using Q learning. When trying to update the replay buffer with experience I am getting the following error: ValueError: Cannot feed value of shape (128,) for Tensor 'Placeholder_1:0', which has shape '(?, 2)' The…
Dee
  • 153
  • 3
  • 15
0
votes
0 answers

Open AI gym and pygame: pygame.error: display Surface quit

I get the common pygame.error: display Surface quit in my _render function as seen below. The gym environment runs, but then crashes after about 10 secs. I am new to pygame so it would help if the error was explained. I have checked here and here,…
luii
  • 319
  • 3
  • 5
  • 16
1 2 3
…
68 69