Adam Villaflor

I am currently a PhD student in the Robotics Institute at Carnegie Mellon University. I have the pleasure to be co-advised by Professors Jeff Schneider and John Dolan.

My main research interests are in deep reinforcement learning and learning behaviors from large offline datasets. I'm particularly interested in how these approaches can be used to address real-world problems like autonomous driving. I received my Bachelor's and Master's at UC Berkeley, where I did research in reinforcement learning for robotics as part of Professors Sergey Levine's and Pieter Abbeel's group.

Email / Resume / Google Scholar

Research

Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
Adam Villaflor, Zhe Huang, Swapnil Pande, John Dolan, Jeff Schneider
ICML, 2022
arxiv / code

BATS: Best Action Trajectory Stitching
Ian Char, Viraj Mehta, Adam Villaflor, John Dolan, Jeff Schneider
NeurIPS Offline Reinforcement Learning Workshop, 2021
arxiv

Learning to Robustly Negotiate Bi-Directional Lane Usage in High-Conflict Driving Scenarios
Christoph Killing, Adam Villaflor, John Dolan
ICRA, 2021
arxiv

Fine-Tuning Offline Reinforcement Learning with Model-Based Policy Optimization
Adam Villaflor, John Dolan, Jeff Schneider
NeurIPS Offline Reinforcement Learning Workshop, 2020
paper

Learning Highway Ramp Merging via Reinforcement Learning with Temporally-Extended Actions
Samuel Triest, Adam Villaflor, John Dolan
IV, 2020
paper

Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
Gregory Kahn*, Adam Villaflor*, Pieter Abbeel, Sergey Levine
CoRL, 2018
arxiv / code

Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
Gregory Kahn, Adam Villaflor, Bosen Ding, Pieter Abbeel, Sergey Levine
ICRA, 2018
arxiv / code

Uncertainty-Aware Reinforcement Learning for Collision Avoidance
Gregory Kahn, Adam Villaflor, Vitchyr Pong, Pieter Abbeel, Sergey Levine
arXiv
arxiv

Template from here!