Minqi Jiang

Minqi Jiang, a PhD student at University College London and Meta AI, explores the intriguing realm of deep reinforcement learning. He shares insights on balancing serendipity with planning in research, along with the implications of Goodhart's Law in decision-making. The discussion dives into the complexities of emergent intelligence and the potential of language models. Minqi highlights the shift towards Software 2.0, challenges in interpretability, and the importance of open-ended research, offering a thought-provoking glimpse into the future of AI technology.

Minqi Jiang is a Ph.D. student at UCL and FAIR, advised by Tim Rocktäschel and Edward Grefenstette. Minqi is interested in how simulators can enable AI agents to learn useful behaviors that generalize to new settings. He is especially focused on problems at the intersection of generalization, human-AI coordination, and open-ended systems. In this episode, we chat about environment and curriculum design for reinforcement learning, model-based RL, emergent communication, open-endedness, and artificial life.

Dr. Minqi Jiang, a researcher in reinforcement learning, and Dr. Marc Rigter, an expert in general-purpose agents, discuss groundbreaking strategies for developing versatile AI agents. They delve into their innovative paper on reward-free curricula, which enhances agents' adaptability through diverse world training. The duo explores challenges in curriculum learning, the importance of effective reward functions, and the balance between creativity and model precision. Their insights pave the way for agents that can excel across various environments, redefining AI's potential.