ai-traineree

The intention is to have a zoo of Deep Reinforcment Learning methods and showcasing their application on some environments.

Read more in the doc: ReadTheDocs AI-Traineree.

Why another Deep Reinforcement Learning framework?

The main reason is the implemention philosophy. We strongly believe that agents should be emerged in the environment and not the other way round. Majority of the popular implementations pass environment instance to the agent as if the agent was the focus point. This might ease implementation of some algorithms but it isn't representative of the world; agents want to control the environment but that doesn't mean they can/should.

That, and using PyTorch instead of Tensorflow or JAX.

Quick start

To get started with training your RL agent you need three things: an agent, an environment and a runner. Let's say you want to train a DQN agent on Gymnasium CartPole-v1:

from aitraineree.agents.dqn import DQNAgent
from aitraineree.runners.env_runner import EnvRunner
from aitraineree.tasks import GymTask

task = GymTask('CartPole-v1')
agent = DQNAgent(task.obs_space, task.action_space)
env_runner = EnvRunner(task, agent)

scores = env_runner.run()

or execute one of provided examples

python -m examples.cart_dqn

That's it.

Installation

PyPi (recommended)

The quickest way to install package is through pip.

pip install ai-traineree

In case you're using uv which is recommended as it makes building environments much faster, use

uv add ai-traineree
# or
# uv pip install ai-traineree

Conda

AI Traineree is also available in Conda via conda-forge channel

conda install -c conda-forge ai-traineree

Source: https://anaconda.org/conda-forge/ai-traineree

Git repository clone

As usual with Python, the expectation is to have own virtual environment and then install project dependencies. For example,

git clone git@github.com:laszukdawid/ai-traineree.git
cd ai-traineree
python -m venv .venv
source .venv/bin/activate
pip install -e .
# or, with uv
# uv sync

Current state

Playing gym

One way to improve learning speed is to simply show them how to play or, more researchy/creepy, provide a proper seed. This isn't a general rule, since some algorithms train better without any human interaction, but since you're on GitHub... that's unlikely your case. Currently there's a script interact.py which uses Gymnasium's play API to record moves and AI Traineree to store them in a buffer. Such buffers can be loaded by agents on initiation.

This is just a beginning and there will be more work on these interactions.

Requirement: Install pygame.

Agents

Multi agents

We provide both Multi Agents agents entities and means to execute them against supported (below) environements. However, that doesn't mean one can be used without the other.

Loggers

Supports using Tensorboard (via PyTorch's SummaryWriter) to display metrics. A lightweight FileLogger is also available for local experiment data.

Environments

Development

We are open to any contributions. If you want to contribute but don't know what then feel free to reach out (see Contact below). The best way to start is through updating documentation and adding tutorials. In addition there are many other things that we know of which need improvement but also plenty that we don't know of.

Setting up development environment is easiest with uv, using the dev dependency group:

uv sync --dev

Typical development commands:

uvx ruff@0.3.0 check
uv run pytest

Contact

Should we focus on something specificallly? Let us know by opening a feature request GitHub issue or contacting through ai-traineree@dawid.lasz.uk.

Citing project

@misc{ai-traineree,
  author = {Laszuk, Dawid},
  title = {AI Traineree: Reinforcement learning toolset},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/laszukdawid/ai-traineree}},
}