Commit c6c18c91 authored by Benjamin's avatar Benjamin
Browse files

clean notebooks outputs

parent 9a1f5a0e
...@@ -20,7 +20,7 @@ We ran a competition using this environment and the associated tests, more detai ...@@ -20,7 +20,7 @@ We ran a competition using this environment and the associated tests, more detai
The environment is built using [Unity ml-agents](https://github.com/Unity-Technologies/ml-agents/tree/master/docs) and contains an agent enclosed in a fixed sized arena. Objects can spawn in this arena, including positive The environment is built using [Unity ml-agents](https://github.com/Unity-Technologies/ml-agents/tree/master/docs) and contains an agent enclosed in a fixed sized arena. Objects can spawn in this arena, including positive
and negative rewards (green, yellow and red spheres) that the agent must obtain (or avoid). All of the hidden tests that will appear in the competition are made using the objects in the training environment. and negative rewards (green, yellow and red spheres) that the agent must obtain (or avoid). All of the hidden tests that will appear in the competition are made using the objects in the training environment.
To get started install the requirements below, and then follow the [Quick Start Guide](documentation/quickstart.md). To get started install the requirements below, and then follow the jupyter notebook tutorials in the [examples folder](examples).
More in depth documentation can be found on the [Documentation Page](documentation/README.md). More in depth documentation can be found on the [Documentation Page](documentation/README.md).
## Development Blog ## Development Blog
......
...@@ -11,12 +11,16 @@ Then you can start a jupyter notebook by running `jupyter notebook` from your te ...@@ -11,12 +11,16 @@ Then you can start a jupyter notebook by running `jupyter notebook` from your te
## Designing arenas ## Designing arenas
For a tutorial on how to design experiments and training configurations we provide a [jupyter notebook](environment_tutorial.ipynb)
You can use `load_config_and_play.py` to visualize a `yml` configuration for an environment arena. Make sure `animalai` You can use `load_config_and_play.py` to visualize a `yml` configuration for an environment arena. Make sure `animalai`
is [installed](../README.md#requirements) and run `python load_config_and_play.py your_configuration_file.yml` which will open the environment in is [installed](../README.md#requirements) and run `python load_config_and_play.py your_configuration_file.yml` which will open the environment in
play mode (control with W,A,S,D or the arrows), close the environment by pressing CTRL+C in the terminal. play mode (control with W,A,S,D or the arrows), close the environment by pressing CTRL+C in the terminal.
## Animalai-train examples ## Animalai-train examples
You will find a training tutorial in this [jupyter notebook](training_tutorial.ipynb)
We provide two scripts which show how to use `animalai_train` to train agents: We provide two scripts which show how to use `animalai_train` to train agents:
- `train_ml_agents.py` uses ml-agents' PPO implementation (or SAC) and can run multiple environments in parralel to speed up - `train_ml_agents.py` uses ml-agents' PPO implementation (or SAC) and can run multiple environments in parralel to speed up
the training process the training process
......
...@@ -35,7 +35,7 @@ ...@@ -35,7 +35,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
...@@ -56,7 +56,7 @@ ...@@ -56,7 +56,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -68,7 +68,7 @@ ...@@ -68,7 +68,7 @@
"<IPython.core.display.HTML object>" "<IPython.core.display.HTML object>"
] ]
}, },
"execution_count": 2, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
......
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment