AI Engineer, PhD
I work on machine learning, reinforcement learning, and large language model systems, from research prototypes to production deployments.
My publications in the field of reinforcement learning, meta-learning, and preference-based learning. These works focus on developing algorithms and methods for efficient adaptation to new tasks and environments.
Applied Intelligence, Springer · 2023
Anand Ballou, Xavier Alameda-Pineda, Chris Reinke
A research paper on variational meta reinforcement learning, focusing on efficient adaptation to new tasks in social robotics.
PhD Thesis, University of Grenoble Alpes · 2024
Anand Ballou
My PhD thesis on the application of meta reinforcement learning to social robotics, exploring variational and preference-based approaches for efficient adaptation to new tasks.
Projects that I developed during my PhD and afterwards. These projects are related to reinforcement learning, meta-learning, and preference-based learning.
A research project on meta reinforcement learning, focusing on variational methods for efficient adaptation to new tasks.
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.
A modular, research-oriented Python library that integrates Reinforcement Learning (specifically Soft Actor-Critic) and Meta-RL (PEARL) with active Preference-Based Learning.