Chen Bo Calvin Zhang
ML Research @ CHAI | Previously @ MIT, ETH Zurich, and University of Manchester
I am currently a research intern at CHAI, where I work with Micah Carroll on reinforcement learning and robustness of large language models.
Before joining CHAI, I was a visiting scholar at MIT, where I focused on online learning and reward design for reinforcement learning. During that time, I was fortunate to collaborate with Zhang-Wei Hong, Aldo Pacchiano, and Pulkit Agrawal.
I hold an MSc in Data Science from ETH Zurich, where I worked with Giorgia Ramponi on preference-based reinforcement learning.
Earlier, I completed my BSc (Hons) in Computer Science and Mathematics at the University of Manchester, where I researched adversarial attacks in deep reinforcement learning under the supervision of Tingting Mu.
I am interested in safe generalization in sequential decision making and AI alignment, with applications to autonomous agents and robotics. I aim to develop algorithms that enable agents to make reliable and safe decisions over long time horizons, even in complex and unpredictable environments.
Google Scholar / Twitter / GitHub / LinkedIn
News
Sep 16, 2024 | A temporary news post for testing purposes only. It will be removed soon. |
---|
Latest Posts
Sep 16, 2024 | The Quantum Cheese Conundrum |
---|
Selected Publications
- ICMLORSO: Accelerating Reward Design via Online Reward Selection and Policy OptimizationIn ICML 2024 Workshop: Aligning Reinforcement Learning Experimentalists and Theorists, 2024
- ICMLHIP-RL: Hallucinated Inputs for Preference-based Reinforcement Learning in Continuous DomainsIn ICML 2023 Workshop: The Many Facets of Preference-Based Learning, 2023