Alexandre Piche
Research Scientist
Human Machine Interaction Through Language
Alexandre Piche is a Senior Research Scientist at ServiceNow Research. He is interested in bridging the gap between academic research in Reinforcement Learning (RL) and applications in energy, education, and enterprise AI. At ServiceNow Research, he focuses on sequential decision making under uncertainty, RL for generative models, and generalization in RL. Alexandre completed his PhD at Mila, Université de Montreal and has previously interned at DeepMind, London, and Riken AIP, Tokyo (remote).
Interests
- Reinforcement Learning
Publications
Causal Discovery with Language Models as Imperfect Experts.
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),
2023.
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels.
International Conference on Machine Learning (ICML),
2023.
Leveraging Human Preferences to Master Poetry.
AAAI Workshops,
2023.
Implicit Offline Reinforcement Learning via Supervised Learning.
Workshop at the Neural Information Processing Systems (NeurIPS),
2022.
Beyond Target Networks: Improving Deep Q-learning with Functional Regularization.
Transactions on Machine Learning Research,
2022.
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels.
Workshop at the International Conference on Machine Learning (ICML),
2022.
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning.
Workshop at the International Conference on Learning Representations (ICLR),
2022.
Planning with Latent SImulated Trajectories.
Workshop at the International Conference on Learning Representations (ICLR),
2019.
Probabilistic Planning with Sequential Monte Carlo Methods.
International Conference on Learning Representations (ICLR),
2019.