CV

A compact version of my CV, you can find the full version of my CV in PDF format here.

Anand BALLOU

AI Engineer, PhD

Paris, France

Designing and developed AI solutions for defense-oriented software involving large-scale heterogeneous data
Building machine learning and deep learning pipelines for data classification, information extraction, and decision support
Integrating LLMs into existing software systems for enhanced natural language understanding and generation capabilities

Variational Meta Reinforcement Learning for Social Robotics, Anand Ballou, Xavier Alameda-Pineda, Chris Reinke. Applied Intelligence, Springer, 2023.
Meta Reinforcement Learning for Social Robotics, Anand Ballou. PhD Thesis, University of Grenoble Alpes, 2024.

Variational Meta Reinforcement Learning: A research project on meta reinforcement learning, focusing on variational methods for efficient adaptation to new tasks.
Social Gym: social_gym is a Python library that provides a benchmark of Gymnasium environments for reinforcement learning, active learning, and preference-based learning in the context of social robotics. It simulates robot interactions in human-populated environments, gaze control, and 2D track racing scenarios.
Preference-Based Learning: PBARL: A modular, research-oriented Python library that integrates Reinforcement Learning (specifically Soft Actor-Critic) and Meta-RL (PEARL) with active Preference-Based Learning.

Variational Meta Reinforcement Learning for Social Robotics, RL@Alpes 2023, 2023-01-03
Preference-Based Adaptive Reinforcement Learning for Social Robotics, Joint Inria Seminar (RobotLearn, Thoth & Morpheo Teams), 2024-09-11