Posts by Collection



Lifelong Inverse Reinforcement Learning

Published in 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.

Download here

Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings

Published in 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.

Download here

Lifelong Learning of Compositional Structures

Published in 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.

Download here

Modular Lifelong Reinforcement Learning via Neural Composition

Published in 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.

Download here

Gap Minimization for Knowledge Sharing and Transfer

Published in 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.

Download here