21 citations · 32 across the 8 of their papers we have counts for
5 papers · 1 filter
Cross-domain Imitation from Observations
Dripta S. Raychaudhuri, Sujoy Paul, Jeroen van Baar +1
Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. With environments modeled as Markov Dec…
Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Sk Miraj Ahmed, Dripta S. Raychaudhuri, Sujoy Paul +2
Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain. However, most of these…
Learning from Trajectories via Subgoal Discovery
Sujoy Paul, Jeroen van Baar, Amit K. Roy-Chowdhury
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories coul…
Trajectory-based Learning for Ball-in-Maze Games
Sujoy Paul, Jeroen van Baar
Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances.…
Adversarial Perturbations Against Real-Time Video Classification Systems
Shasha Li, Ajaya Neupane, Sujoy Paul +4
Recent research has demonstrated the brittleness of machine learning systems to adversarial perturbations. However, the studies have been mostly limited to perturbations on images…