GitHub
9eb3f049
Cleanup unused code in TrainerController (#2315)
* Removes unused SubprocessEnvManager import in trainer_controller * Removes unused `steps` argument to `TrainerController._save_model` * Consolidates unnecessary branching for curricula in `TrainerController.advance` * Moves `reward_buffer` into `TFPolicy` from `PPOPolicy` and adds `BCTrainer` support so that we don't have a broken interface / undefined behavior when BCTrainer is used with curricula. |
5 年前 | |
---|---|---|
.. | ||
mlagents/trainers | Cleanup unused code in TrainerController (#2315) | 5 年前 |
README.md | Fixing tables in documentation and other markdown errors. (#1199) | 6 年前 |
setup.py | Fixed the import issue (#2158) | 6 年前 |
README.md
Unity ML-Agents Python Interface and Trainers
The mlagents
Python package is part of the
ML-Agents Toolkit.
mlagents
provides a Python API that allows direct interaction with the Unity
game engine as well as a collection of trainers and algorithms to train agents
in Unity environments.
The mlagents
Python package contains two sub packages:
-
mlagents.envs
: A low level API which allows you to interact directly with a Unity Environment. See here for more information on using this package. -
mlagents.trainers
: A set of Reinforcement Learning algorithms designed to be used with Unity environments. Access them using the:mlagents-learn
access point. See here for more information on using this package.
Installation
Install the mlagents
package with:
pip install mlagents
Usage & More Information
For more detailed documentation, check out the ML-Agents Toolkit documentation.