Designed an RL environment where 16 agents use a shared policy learn to self-organise into compact formations using only local observations and density rewards. Explores emergent coordination in a symmetric multi-agent system.
UCL MSc Machine Learning Thesis and NeurIPS 2022 Workshop paper: Learning directed acyclic graphs by backpropagation
Developed a framework for learning directed acyclic graphs (DAGs) via discrete backpropagation, testing it on synthetic and real data, with competitive results which proved the concept.
Gave as contributed talk at NeurIPS 2022 workshop.
MSc Statistical Natural Language Processing group project: Learning from clue structure to solve cryptic crosswords
Originated and coded structural ideas we used for our solver. This enabled us to get very close to state-of-the-art mid-size transformer performance – with only a relatively small dataset. Outstanding Distinction.
Developed two reinforcement learning agents who “invent” a language to communicate a varying random message successfully. Agent “Alice” had to ceeate a binary code language, and Agent “Bob” had to learn to understand it. They did so without any outside help, using only knowledge of how close Bob’s guess was in each step of the game.
Processed astrophysical data and built a neural net to predict the mass of supermassive black holes from their “quasar” emissions. Within the distribution of quasars I was targeting, this achieved predictions to within current observational estimates.