[F22] Reinforcement Learning Final Exam at Innopolis university
Before you begin, ensure you have met the following requirements:
- You have installed the latest version of
Python
- You have a
Windows/Linux/Mac
machine. - You have read
README.md
. - Optional: You have
Docker
anddocker-compose
installed.
If you have docker on your machine then you can skip to the next section.
To install requirements, follow these steps:
conda create -n bot python=3.9 -y && conda activate bot
pip install -r requirements.txt
python -u app.py
To use Docker, follow these steps:
docker build -t bot .
docker run -it --rm bot
or
docker-compose up -d --build
docker-compose logs # to see logs
Let me show you some chatbot's results:
If there is an answer to the question in the base of the bot, the bot will answer.
You can improve the bot's response by giving feedback, select one of the "Yes" and "No" buttons below.
The question is sent to the admins, and when they receive the answer, they add it to the database.
you can find more results from chatbot in this directory neural networks' configs of those results are described in the filename
Framework divides into tow main parts:
- User Simulator
- End-to-End Neural Dialogue system