AI Research Intern - Reinforcement Learning

The Internship In Short

Join the artificial intelligence team at Multitel and explore the latest advances in Reinforcement Learning (RL) and eXplainable Reinforcement Learning (XRL). During this internship, you will investigate how RL and XRL can be used to control optimally the energy management system of an energy community to optimize metrics such as energy auto-consumption or electricity costs. You will work on state-of-the-art AI techniques and contribute to research in RL and XRL in the field of energy communities and energy management systems.

The topic

An energy community is a group of citizens, businesses, or local organizations that work together to produce, consume, store, or share energy locally. By coordinating resources such as solar panels, batteries, and flexible electricity consumption, energy communities can increase the use of renewable energy, reduce energy costs, and improve local energy resilience. They also encourage active participation in the energy transition by allowing members to collectively manage and benefit from local energy resources.

Reinforcement learning (RL) is an emerging field in AI where an agent learns to behave optimally in its environment. It learns by taking successive decisions, aka actions, and receiving feedback under the form of a numerical reward that must be maximized over a series of steps. The difference with a more standard use of supervised learning AI is that the agent creates his training data himself, by picking actions, experiencing their effect on the environment and by observing which state he ends up in.  

What you will work on:

You will explore several research questions, including:

• How can RL be used to optimize the control of an energy community?
• Which XRL methods can help developers or users understand the agent's choices?
• How to use an external software as a simulator, that can be in a different language, while the AI training loop is in Python ?

As an intern, you will play an integral role in the research and development of RL agents to address this key problem. Responsibilities include:

• Conducting an in-depth literature review;
• Implementing and fine-tuning state-of-the-art RL models (DDPG, DDQN) for energy community control;
• Implement XRL methods to better understand your agents, from the developers or end user perspective;
• Benchmarking the performance of your agents against conventional optimization solutions;
• Documenting and presenting your results.

The profile we are looking for:

We are looking for a motivated student who is curious about AI research and enjoys turning ideas into working solutions.

You should have:

1. A background in Computer Science, Artificial Intelligence, Data Science, or a related field, typically through an engineering degree or university program.
2. A strong interest in Artificial Intelligence and Dynamic Programing, particularly in recent developments in Reinforcement Learning.
3. Fluency in English is mandatory; proficiency in French is a plus.
4. Experience with machine learning or AI projects.
5. Good programming skills in Python.
6. A basic foundation in probability and statistics.
7. Knowledge of PyTorch or another deep learning framework.
8. Basic knowledge of Git and software version control.
9. Working proficiency with Linux and Docker is a plus.
10. A self-starter mindset, with the ability to work both independently and as part of a team.
11. A curious and analytical approach to solving complex problems.
12. Attention to detail and commitment to producing robust, reproducible results.

Experience with RL and XRL is a plus, but a strong motivation to learn is equally valued.

Even if you don’t check every box in our requirements, we encourage you to apply. We value diverse backgrounds, curiosity, and the drive to learn, grow, and achieve.

Recruitment Process:

1. Application Review

We review your CV and cover letter to assess your background, skills, and interest in the internship topic.

2. Interview

Selected candidates are invited to an interview combining a technical discussion with a conversation about the internship objectives, your interests, and your expectations.

3. Following the interview

We select the candidate whose profile and interests best match the internship.