Daniel Melcer
(he/him/his)
PhD Student
Research interests
- Reinforcement learning
- Formal methods
- Machine learning
- Programming languages
Education
- BS in Computer Science, Northeastern University
Biography
Daniel Melcer is a doctoral student at the Khoury College of Computer Sciences at Northeastern University, advised by Stavros Tripakis and Christopher Amato.
Melcer concluded his undergraduate computer science degree at Khoury College in 2021, then began his doctoral work. That research, projected to run until 2026, focuses on the intersection of formal methods and reinforcement learning. He is affiliated with the Formal Methods Group, as well as the Lab for Learning and Planning in Robotics.
Labs and groups
Recent publications
-
Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments
Citation: Daniel Melcer, Christopher Amato, Stavros Tripakis. (2024). Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments RLJ, 4, 1965-1994. https://rlj.cs.umass.edu/2024/papers/Paper254.html -
ProofViz: An Interactive Visual Proof Explorer
Citation: Daniel Melcer and Stephen Chang. (2021). "ProofViz: An Interactive Visual Proof Explorer". In Zsók, V., Hughes, J. (eds) Trends in Functional Programming. TFP 2021. Lecture Notes in Computer Science(), vol 12834. Springer, Cham. DOI: 10.1007/978-3-030-83978-9_6 -
Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search
Citation: A Velasquez, B Bissey, L Barak, A Beckus, I Alkhouri, D Melcer, and G Atia. (2021). Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 12015-12023. DOI: 10.1609/aaai.v35i13.17427 -
Verification-Guided Tree Search
Citation: Alvaro Velasquez and Daniel Melcer. 2020. Verification-Guided Tree Search. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '20). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 2026–2028.