Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning

1 code implementation • 13 Jul 2023 • Marcel Hussing, Jorge A. Mendez, Anisha Singrodia, Cassandra Kent, Eric Eaton

We provide training and evaluation settings for assessing an agent's ability to learn compositional task policies.

Benchmarking Offline RL +2

A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

no code implementations • 18 Jan 2023 • Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sébastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha

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 encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.

Lifelong Machine Learning of Functionally Compositional Structures

1 code implementation • 25 Jul 2022 • Jorge A. Mendez

Supervised learning evaluations found that 1) compositional models improve lifelong learning of diverse tasks, 2) the multi-stage process permits lifelong learning of compositional knowledge, and 3) the components learned by the framework represent self-contained and reusable functions.

BIG-bench Machine Learning Continual Learning +1

How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition

no code implementations • 15 Jul 2022 • 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.

Continual Learning

CompoSuite: A Compositional Reinforcement Learning Benchmark

1 code implementation • 8 Jul 2022 • Jorge A. Mendez, Marcel Hussing, Meghna Gummadi, Eric Eaton

We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Modular Lifelong Reinforcement Learning via Neural Composition

1 code implementation • ICLR 2022 • Jorge A. Mendez, Harm van Seijen, Eric Eaton

Empirically, we demonstrate that neural composition indeed captures the underlying structure of this space of problems.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings

no code implementations • 3rd Conversational AI Workshop at 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) 2019 • Jorge A. Mendez, Alborz Geramifard, Mohammad Ghavamzadeh, Bing Liu

Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for real-world applications.

reinforcement-learning Reinforcement Learning (RL)

Lifelong Inverse Reinforcement Learning

1 code implementation • NeurIPS 2018 • Jorge A. Mendez, Shashank Shivkumar, Eric Eaton

Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user.

reinforcement-learning Reinforcement Learning (RL)

SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries

1 code implementation • 28 Jun 2022 • Meghna Gummadi, David Kent, Jorge A. Mendez, Eric Eaton

Inspired by natural learners, we introduce a Sparse High-level-Exclusive, Low-level-Shared feature representation (SHELS) that simultaneously encourages learning exclusive sets of high-level features and essential, shared low-level features.

Class Incremental Learning Incremental Learning +2

Lifelong Learning of Compositional Structures

1 code implementation • ICLR 2021 • 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 structurally related problems.

Continual Learning

Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting

2 code implementations • NeurIPS 2020 • Jorge A. Mendez, Boyu Wang, Eric Eaton

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems.

Policy Gradient Methods