Research

Publications (* denotes equal authorship):

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization. Brandon Trabucco, Aviral Kumar, Young Geng, Sergey Levine. In Machine Learning For Structural Biology Workshop, Neural Information Processing Systems, 2020. (poster)

Conservative Objective Models: A Simple Approach to Model-Based Optimization. Brandon Trabucco, Aviral Kumar, Young Geng, Sergey Levine. In Offline Reinforcement Learning Workshop, Neural Information Processing Systems, 2020. (poster)

Discovering Autoregressive Orderings with Variational Inference. Simon Li*, Brandon Trabucco*, Michael Luo, Seth Park, Yang Gao, Sheng Shen, Trevor Darrell. Under review, Submitted to International Conference on Learning Representations, 2021. (ratings in top 7% of submissions)

Inter-Level Cooperation in Hierarchical Reinforcement Learning. Abdul Kreidieh, Glen Berseth, Brandon Trabucco, Samyak Parajuli, Sergey Levine, Alexandre M. Bayen. In Deep Reinforcement Learning Workshop, Neural Information Processing Systems, 2020. (poster)

Synthetic Datasets for Neural Program Synthesis. Richard Shin, Neel Kant, Kavi Gupta, Christopher Bender, Brandon Trabucco, Rishabh Singh, Dawn Song. In International Conference on Learning Representations, 2019. (poster)