You can also find my articles on my Google Scholar profile.
PDF
Preprint, 2022
We survey the mostly disjoint fields of lifelong or continual learning and compositional learning, and draw connections between them.
PDF
Neural Networks, 2023
We propose a unified approach to assess the performance of lifelong learning approaches, agnostic to the specific domain or technique used for learning.
PDF
Journal of Machine Learning Research (JMLR), 2023
We extended the notion of performance gap for measuring domain discrepancy (NeurIPS-19) to a variety of transfer and multi-task learning settings, and introduced two new algorithms based on this notion for improving transfer and multi-task learning performance.
PDF Code
Conference on Lifelong Learning Agents (CoLLAs), 2022
We introduce SHELS, a combined framework that supports class-incremental continual learning without the specification of explicit class boundaries by performing out-of-distribution detection.
PDF Code
Conference on Lifelong Learning Agents (CoLLAs), 2022
We introduce CompoSuite, a robotic manipulation benchmark with hundreds of tasks for evaluating the functional compositionality of RL algorithms.
PDF Code
International Conference on Learning Representations (ICLR), 2022
We explore the problem of lifelong RL of functionally compositional knowledge, and develop an algorithm that demonstrates zero-shot and forward transfer, avoidance of forgetting, and backward transfer in discrete 2-D and robotic manipulation domains.
PDF Code Video
International Conference on Learning Representations (ICLR), 2021
We study the question of how to learn compositional parameterized structures from an empirical standpoint, and propose a general-purpose framework that can learn with various forms of knowledge representations and base algorithms.
PDF Code
Advances in Neural Information Processing Systems (NeurIPS), 2020
We introduced an algorithm for directly optimizing factored policies via policy gradients in a lifelong learning setting, and showed theoretically and empirically that our approach avoids catastrophic forgetting.
PDF Code Poster
Advances in Neural Information Processing Systems (NeurIPS), 2019
We introduced the notion of performance gap as a label-dependent notion of domain discrepancy, and developed an boosting-based algorithm, gapBoost, that exploits the insights from gap minimization.
PDF Code Video Poster
Advances in Neural Information Processing Systems (NeurIPS), 2018
We introduced the problem of lifelong learning from demonstrations, and created an efficient lifelong inverse reinforcement learning (ELIRL) algorithm.
PDF Code
CoRL 2022 Workshop on Pre-training Robot Learning, 2022
We propose and release a variety of data sets for compositional off-line RL on CompoSuite
PDF Video
3rd Conversational AI Workshop at Neural Information Processing Systems (ConvAI-NeurIPS), 2019
We developed an architecture for learning multi-domain task oriented dialog policies, based on the notion of action embeddings, which capture domain agnostic representations of how to respond to user's queries.
PDF
University of Pennsylvania, 2022
This dissertation presents an in-depth treatment of the problems of lifelong or continual learning and compositional knowledge representations, which had so far been studied separately.