Homanga Bharadhwaj

TL;DR: This work designs a recommendation framework that is trained to be reasonably good enough for a wide range of users and handles the user cold-start model much better than state-of-the art benchmark recommender systems.

TL;DR: This paper theoretically characterize the tradeoff between safety and policy improvement, show that the safety constraints are likely to be satisfied with high probability during training, derive provable convergence guarantees for the approach, and demonstrate the efficacy of the proposed approach on a suite of challenging navigation, manipulation, and locomotion tasks.

TL;DR: This work uses customized Gated Recurrent Unit cells to capture latent features of users and items observable from short-term and long-term temporal profiles and proposes a Recurrent Generative Adversarial Network (RecGAN), which outperforms other baseline models irrespective of user behavior and density of training data.

TL;DR: This work proposes and studies multiple complementary learning tasks, targeting conceptually different data relationships by only resorting to the available training samples and labels of a standard DML setting, resulting in strong generalization and state-of-the-art performance on multiple established DML benchmark datasets.

TL;DR: This work introduces a robust framework that plans in simulation and transfers well to the real environment, consisting of the encoder and planner modules, and shows successful planning performances in different navigation tasks.