* Hotfix on Gym and the notebooks
* REMOVING THE PROTO GENERATION TESTS
* REMOVING THE PROTO GENERATION TESTS
* Update notebooks/getting-started-gym.ipynb
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Trying to enforce nuget version
* Update notebooks/getting-started-gym.ipynb
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Removing proto_generation
* Update notebooks/getting-started-gym.ipynb
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Update docstring
Co-authored-by: Chris Elion <celion@gmail.com>
"The first five steps show how to use the `UnityEnv` wrapper with single-agent environments. See below step five for how to use with multi-agent environments."
"These steps show how to use the `UnityEnv` wrapper with single-agent environments. See section below for how to use with multi-agent environments."
]
},
{
"### 1. Load dependencies\n",
"### 1.Set environment parameters\n",
"Be sure to set `env_name` to the name of the Unity environment file you want to launch.\n",
"\n",
"__Note__ : All the example environments have multiple agents by default. You can disable the duplicates in the inspector before building the executable."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"env_name = \"../envs/GridWorldSingle\" # Name of the Unity environment binary to launch"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2. Load dependencies\n",
"\n",
"The following loads the necessary dependencies and checks the Python version (at runtime). ML-Agents Toolkit (v0.3 onwards) requires Python 3."
]
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2. Start the environment\n",
"`UnityEnv` launches and begins communication with the environment when instantiated. We will be using the `GridWorld` environment. You will need to create an `envs` directory within the `/python` subfolder of the repository, and build the GridWorld environment to that directory. For more information on building Unity environments, see [here](../docs/Learning-Environment-Executable.md)."
"### 3. Start the environment\n",
"`UnityEnv` launches and begins communication with the environment when instantiated. We will be using the `GridWorld` environment. You will need to create an `envs` directory in the root directory of the repository, and build the GridWorld environment to that directory. For more information on building Unity environments, see [here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Executable.md)."
]
},
{
"outputs": [],
"source": [
"env_name = \"../envs/GridWorld\" # Name of the Unity environment binary to launch\n",
"### 3. Examine the observation and state spaces\n",
"### 4. Examine the observation and state spaces\n",
"We can reset the environment to be provided with an initial observation of the environment."
]
},
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4. Take random actions in the environment\n",
"### 5. Take random actions in the environment\n",
"Once we restart an environment, we can step the environment forward and provide actions to all of the agents within the environment. Here we simply choose random actions using the `env.action_space.sample()` function.\n",
"\n",
"Once this cell is executed, 10 messages will be printed that detail how much reward will be accumulated for the next 10 episodes. The Unity environment will then pause, waiting for further signals telling it what to do next. Thus, not seeing any animation is expected when running this cell."
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5. Close the environment when finished\n",
"### 6. Close the environment when finished\n",
"When we are finished using an environment, we can close it with the function below."
GitHub
4 年前