Machine learning – How to create a new gym environment in Openai?

gym-foo/
 README.md
 setup.py
 gym_foo/
 __init__.py
 envs/ 
 __init__.py
 foo_env.py
 foo_extrahard_env.py

class FooEnv(gym.Env ):
 metadata = {'render.modes': ['human']}

 def __init__(self):
 pass

 def _step (self, action):
 """

 Parameters
 ----------
 action :

 Returns
 -------
 ob, reward, episode_over, info: tuple
 ob (object) :
 an environment-specific object representing your observation of
 the environment.
 reward (float) :
 amount of reward achieved by the previous action. The scale
 varies between environments, but the goal is always to increase
 your total reward.
 episode_over (bool) :
 whether it's time to reset the environment again. Most (but not
 all) tasks are divided up into well-defined episodes, and done
 being True indicates the episode has terminated. (For example,
 perhaps the pole tipped too far, or you lost your last life.)
 info (dict) :
 diagnostic information useful for debugging. It can sometimes
 be useful for learning (for example, it might contain the raw
 probabilities behind the environment's last state change).
 However, official evaluations of your agent are not allowed to
 use this for learning.
 """
 self._take_action(action)
 self.status = self.env .step()
 reward = self._get_reward()
 ob = self.env.getState()
 episode_over = self.status != hfo_py.IN_GAME
 return ob, reward , episode_over, {}

 def _reset(self):
 pass

 def _render(self, mode='human', close=False):
 pass

 def _take_action(self, action):
 pass

 def _get_reward(self):
 """ Reward is given for XY . """
 if self.status == FOOBAR:
 return 1
 elif self.status == ABC:
 return self.somestate ** 2
 else :
 return 0

import gym
import gym_foo
env = gym.make( 'MyEnv-v0')

I have a task to make an AI agent and learn to use ML to play video games. I want to use OpenAI Gym to create a new environment because I don’t want to Use existing environment. How to create a new custom environment?

Also, is there any other way I can start AI Agent to play certain video games without the help of OpenAI Gym?

Check out my banana-gym in a very small environment.

Create a new Environment

See the main page of the repository:

https://github.com/openai/gym/blob/master/docs/creating-environments.md

The steps are:

>Create a new repository using the PIP package structure

It should look like this

gym-foo/
 README.md
 setup.py
 gym_foo/
 __init__.py
 envs/
 __init__.py
 foo_env .py
 foo_extrahard_env.py

For its content, please click on the link above. The details not mentioned there especially what some functions in foo_env.py should look like. View the example and It is helpful at gym.openai.com/docs/. Here is an example:

class FooEnv(gym.Env):
 metadata = {'render. modes': ['human']}

 def __init__(self):
 pass
 def _step(self, action):
 "" "
 Parameters
 ----------
 action :
 Returns
 ------- 
 ob, reward, episode_over, info: tuple
 ob (object) :
 an environment-specific object representing your observation of 
 the environment.
 reward (float) :
 amount of reward achieved by the previous action. The scale
 varies between environments, but the goal is always to increase
 your total reward.
 episode_over (bool) :
 whether it's time to reset the environment again. Most (but not
 all) tasks are divided up into well-defined episodes, and done
 being True indicates the episode has terminated. (For example,
 perhaps the pole tipped too far, or you lost your last life.)
 info (dict) :
 diagnostic information useful for debugging. It can sometimes
 be useful for learning (for example, it might contain the raw
 probabilities behind the environment's last state change).
 However, official evaluations of your agent are not allowed to
 use this for learning.
 """
 self._take_action(action)
 self.status = self.env.step()
 reward = self._get_reward()
 ob = self.env.getState()
 episode_over = self.status != hfo_py.IN_GAME
 return ob, reward, episode_over, {}
 def _reset(self):
 pass
 def _render(self, mode='human', close=False):
 pass
 def _take_action(self, action):
 pass
 def _get_reward(self):
 """ Reward is given for XY. """
 if self.status == FOOBAR:
 return 1
 elif self.status == ABC:
 return self.somestate ** 2
 else:
 return 0 
Use your environment

import gym
import gym_foo
env = gym.make('MyEnv-v0')
Example
> https://github.com/openai/gym-soccer
> https://github.com/ope nai/gym-wikinav
> https://github.com/alibaba/gym-starcraft
> https://github.com/endgameinc/gym-malware
> https://github.com /hackthemarket/gym-trading
> https://github.com/tambetm/gym-minecraft
> https://github.com/ppaquette/gym-doom
> https://github. com/ppaquette/gym-super-mario
> https://github.com/tuzzer/gym-maze