17 citations · 84 across the 13 of their papers we have counts for
13 papers
Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning
Marcel Hussing, Jorge A. Mendez, Anisha Singrodia +2
Offline reinforcement learning (RL) is a promising direction that allows RL agents to pre-train on large datasets, avoiding the recurrence of expensive data collection. To advance…
Embodied Lifelong Learning for Task and Motion Planning
Jorge Mendez-Mendez, Leslie Pack Kaelbling, Tomás Lozano-Pérez
A robot deployed in a home over long stretches of time faces a true lifelong learning problem. As it seeks to provide assistance to its users, the robot should leverage any accumul…
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Megan M. Baker, Alexander New, Mario Aguilar-Simon +44
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks enc…
Lifelong Machine Learning of Functionally Compositional Structures
Jorge A. Mendez
A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and reuse them in novel combinations for solving different problems. Learning such c…
CompoSuite: A Compositional Reinforcement Learning Benchmark
Jorge A. Mendez, Marcel Hussing, Meghna Gummadi +1
We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL). Each CompoSuite task requires a particular…
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition
Jorge A. Mendez, Eric Eaton
A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general understanding of the world. Such an agent would require the ability to continually…
Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings
Jorge A. Mendez, Alborz Geramifard, Mohammad Ghavamzadeh +1
Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for re…
Lifelong Inverse Reinforcement Learning
Jorge A. Mendez, Shashank Shivkumar, Eric Eaton
Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user. However, even for a single task, LfD may require numerous demon…
Modular Lifelong Reinforcement Learning via Neural Composition
Jorge A. Mendez, Harm van Seijen, Eric Eaton
Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse o…
SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries
Meghna Gummadi, David Kent, Jorge A. Mendez +1
While deep neural networks (DNNs) have achieved impressive classification performance in closed-world learning scenarios, they typically fail to generalize to unseen categories in…
Gap Minimization for Knowledge Sharing and Transfer
Boyu Wang, Jorge Mendez, Changjian Shui +5
Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information fro…
Lifelong Learning of Compositional Structures
Jorge A. Mendez, Eric Eaton
A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structural…
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
Jorge A. Mendez, Boyu Wang, Eric Eaton
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require bef…