Wilka Torrico Carvalho — accepted AI-conference papers

2023

Composing Task Knowledge With Modular Successor Feature Approximators

Wilka Torrico Carvalho, Angelos Filos, Richard Lewis, Honglak Lee, Satinder Singh

ICLR 2023poster

Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing and transferring predictive knowledge and behavior. SF&GPI works by having an agent learn predictive representations (SFs) that can be combined for transfer to…

Cited by 12 Source ↗PDF ↗Scholar ↗

2021

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

Christopher Hoang, Sungryull Sohn, Jongwook Choi, Wilka Torrico Carvalho, Honglak Lee

NeurIPS 2021poster

Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially challenging for long-horizon goals. Current methods have tackle…

Cited by 42 Source ↗PDF ↗Scholar ↗