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
13
votes
2 answers

How to pass arguments to openai-gym environments upon init

Following this (unreadable) forum post, I thought it was fitting to post it up on stack overflow for future generations who search for it. How to pass arguments for gym environments on init?
Gulzar
  • 23,452
  • 27
  • 113
  • 201
13
votes
3 answers

How can I register a custom environment in OpenAI's gym?

I have created a custom environment, as per the OpenAI Gym framework; containing step, reset, action, and reward functions. I aim to run OpenAI baselines on this custom environment. But prior to this, the environment has to be registered on OpenAI…
Mad_Scientist
  • 195
  • 1
  • 1
  • 8
13
votes
1 answer

Why can't my DQN agent find the optimal policy in a non-deterministic environment?

edit: The following seems also to be the case for FrozenLake-v0. Please note that I'm not interested in simple Q-learning as I want to see solutions that work with continuous observation spaces. I recently created the banana_gym OpenAI environment.…
Martin Thoma
  • 124,992
  • 159
  • 614
  • 958
12
votes
1 answer

How to implement custom environment in keras-rl / OpenAI GYM?

I'm a complete newbie to Reinforcement Learning and have been searching for a framework/module to easily navigate this treacherous terrain. In my search I've come across two modules keras-rl & OpenAI GYM. I can get both of them two work on the…
Manipal King
  • 422
  • 1
  • 5
  • 18
10
votes
2 answers

OpenAI GYM's env.step(): what are the values?

I am getting to know OpenAI's GYM (0.25.1) using Python3.10 with gym's environment set to 'FrozenLake-v1 (code below). According to the documentation, calling env.step() should return a tuple containing 4 values (observation, reward, done, info).…
doesnotcompile
  • 103
  • 1
  • 1
  • 7
10
votes
1 answer

I'm getting an error with env rendering - env.render()

I was trying to implement Atari Games while rendering I get an error as given below: line 283, in render raise error.Error( gym.error.Error: render(mode='human') is deprecated. Please supply `render_mode` when constructing your environment,…
Natasha
  • 351
  • 1
  • 2
  • 10
10
votes
2 answers

OpenAI gym player mode

Does anyone know how to run one of the OpenAI gym environments as a player. As in letting a human player play a round of cart pole? I have seen that there is env.mode = 'human' but I have not been able to get it to run properly. I have tried to…
user3704648
  • 349
  • 3
  • 14
10
votes
1 answer

OpenAI gym mujoco ImportError: No module named 'mujoco_py.mjlib'

I try to run this code in openAi gym. but it can not. import mujoco_py import gym from os.path import dirname env = gym.make('Hopper-v1') env.reset() for _ in range(1000): env.render() env.step(env.action_space.sample()) the error…
Yunfan Lu
  • 103
  • 1
  • 1
  • 5
10
votes
2 answers

How to install OpenAI Universe without getting error code 1 on Windows?

When I try to install OpenAi Universe on my Windows machine via python pip I get following stacktrace: Traceback (most recent call last): File "", line 1, in File…
creativecreatorormaybenot
  • 114,516
  • 58
  • 291
  • 402
9
votes
2 answers

how to create an OpenAI Gym Observation space with multiple features

Using Python3.6, Ubuntu 18.04, Gym 0.15.4, RoS melodic, Tensorflow 1.14 and rl_coach 1.01: I have built a custom Gym environment that is using a 360 element array as the observation_space. high = np.array([4.5] * 360) #360 degree scan to a max of…
learningtofly
  • 353
  • 1
  • 2
  • 13
9
votes
1 answer

Why unwrap an openAI gym?

I'm trying to get some insights into reinforcement learning while using openAI gym as a learning environment. I do this by reading the book Hands-on reinforcement learning with Python. In this book, some code is provided. Often, the code doesn't…
Bram Janssens
  • 101
  • 1
  • 4
9
votes
1 answer

Get name / id of a OpenAI Gym environment

Given: import gym env = gym.make('CartPole-v0') How do I get CartPole-v0 in a way that works across any Gym env?
Andrew Schreiber
  • 14,344
  • 6
  • 46
  • 53
9
votes
5 answers

Can't import gym; ModuleNotFoundError: No module named 'gym'

Can't import gym; ModuleNotFoundError: No module named 'gym'
yyt
  • 91
  • 1
  • 1
  • 2
9
votes
5 answers

openAI Gym NameError in Google Colaboratory

I've just installed openAI gym on Google Colab, but when I try to run 'CartPole-v0' environment as explained here. Code: import gym env = gym.make('CartPole-v0') for i_episode in range(20): observation = env.reset() for t in range(100): …
Javier A. Zambrano Macias
  • 158
  • 1
  • 1
  • 6
9
votes
1 answer

Error following env.render() for OpenAI

I am trying to get the code below to work. import gym env = gym.make("CartPole-v0") env.reset() env.render() I have no problems running the first 3 lines but when I run the 4th I get the error: Traceback (most recent call last): File…
MikeDoho
  • 552
  • 2
  • 5
  • 18
1
2
3
…
68 69