Search Results for author: Eric Eaton

Found 33 papers, 12 papers with code

Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence

no code implementations9 Mar 2024 Marcel Hussing, Claas Voelcker, Igor Gilitschenski, Amir-Massoud Farahmand, Eric Eaton

We show that deep reinforcement learning can maintain its ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples.

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

1 code implementation4 Oct 2023 Pengyuan Lu, Michele Caprio, Eric Eaton, Insup Lee

Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address task trade-off preferences with zero-shot.

Continual Learning Image Classification +1

A Metacognitive Approach to Out-of-Distribution Detection for Segmentation

no code implementations4 Oct 2023 Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton

Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world.

Out-of-Distribution Detection Out of Distribution (OOD) Detection +2

Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning

1 code implementation13 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

CAROM Air -- Vehicle Localization and Traffic Scene Reconstruction from Aerial Videos

no code implementations31 May 2023 Duo Lu, Eric Eaton, Matt Weg, Wei Wang, Steven Como, Jeffrey Wishart, Hongbin Yu, Yezhou Yang

Road traffic scene reconstruction from videos has been desirable by road safety regulators, city planners, researchers, and autonomous driving technology developers.

Autonomous Driving

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

1 code implementation24 May 2023 Pengyuan Lu, Michele Caprio, Eric Eaton, Insup Lee

Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address task trade-off preferences with zero-shot.

Continual Learning Image Classification +1

Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning

no code implementations4 Dec 2022 Marcel Hussing, Karen Li, Eric Eaton

Satellite image analysis has important implications for land use, urbanization, and ecosystem monitoring.

Contrastive Learning Transfer Learning

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

no code implementations15 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 implementation8 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)

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 implementation28 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

Gap Minimization for Knowledge Sharing and Transfer

no code implementations26 Jan 2022 Boyu Wang, Jorge Mendez, Changjian Shui, Fan Zhou, Di wu, Gezheng Xu, Christian Gagné, Eric Eaton

Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.

Representation Learning Transfer Learning

Mako: Semi-supervised continual learning with minimal labeled data via data programming

no code implementations29 Sep 2021 Pengyuan Lu, Seungwon Lee, Amanda Watson, David Kent, Insup Lee, Eric Eaton, James Weimer

This tool achieves similar performance, in terms of per-task accuracy and resistance to catastrophic forgetting, as compared to fully labeled data.

Continual Learning Image Classification

Towards a theory of out-of-distribution learning

no code implementations29 Sep 2021 Ali Geisa, Ronak Mehta, Hayden S. Helm, Jayanta Dey, Eric Eaton, Jeffery Dick, Carey E. Priebe, Joshua T. Vogelstein

This assumption renders these theories inadequate for characterizing 21$^{st}$ century real world data problems, which are typically characterized by evaluation distributions that differ from the training data distributions (referred to as out-of-distribution learning).

Learning Theory

Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

3 code implementations12 Jun 2021 Kyle Vedder, Eric Eaton

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse.

Birds Eye View Object Detection Object Detection

Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer

no code implementations ICML Workshop LifelongML 2020 Seungwon Lee, Sima Behpour, Eric Eaton

In deep networks, transferring the appropriate granularity of knowledge is as important as the transfer mechanism, and must be driven by the relationships among tasks.

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 Learning of Factored Policies via Policy Gradients

no code implementations ICML Workshop LifelongML 2020 Jorge A Mendez, Eric Eaton

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

Continuous Control Policy Gradient Methods

Transfer Learning via Minimizing the Performance Gap Between Domains

1 code implementation NeurIPS 2019 Boyu Wang, Jorge Mendez, Mingbo Cai, Eric Eaton

We propose a new principle for transfer learning, based on a straightforward intuition: if two domains are similar to each other, the model trained on one domain should also perform well on the other domain, and vice versa.

Generalization Bounds Transfer Learning

Zero-Shot Image Classification Using Coupled Dictionary Embedding

no code implementations10 Jun 2019 Mohammad Rostami, Soheil Kolouri, Zak Murez, Yuri Owekcho, Eric Eaton, Kuyngnam Kim

Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes.

Attribute Classification +5

Artificial Intelligence for Pediatric Ophthalmology

no code implementations6 Apr 2019 Julia E. Reid, Eric Eaton

KEYWORDS: pediatric ophthalmology, machine learning, artificial intelligence, deep learning

BIG-bench Machine Learning Image Generation

Tree-Structured Boosting: Connections Between Gradient Boosted Stumps and Full Decision Trees

no code implementations18 Nov 2017 José Marcio Luna, Eric Eaton, Lyle H. Ungar, Eric Diffenderfer, Shane T. Jensen, Efstathios D. Gennatas, Mateo Wirth, Charles B. Simone II, Timothy D. Solberg, Gilmer Valdes

Additive models, such as produced by gradient boosting, and full interaction models, such as classification and regression trees (CART), are widely used algorithms that have been investigated largely in isolation.

Additive models General Classification

Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer

no code implementations10 Oct 2017 David Isele, Mohammad Rostami, Eric Eaton

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer.

BIG-bench Machine Learning Dictionary Learning +2

Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition

no code implementations15 Sep 2017 Mohammad Rostami, Soheil Kolouri, Kyungnam Kim, Eric Eaton

Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience.

Multi-Task Learning

Blue Sky Ideas in Artificial Intelligence Education from the EAAI 2017 New and Future AI Educator Program

no code implementations1 Feb 2017 Eric Eaton, Sven Koenig, Claudia Schulz, Francesco Maurelli, John Lee, Joshua Eckroth, Mark Crowley, Richard G. Freedman, Rogelio E. Cardona-Rivera, Tiago Machado, Tom Williams

The 7th Symposium on Educational Advances in Artificial Intelligence (EAAI'17, co-chaired by Sven Koenig and Eric Eaton) launched the EAAI New and Future AI Educator Program to support the training of early-career university faculty, secondary school faculty, and future educators (PhD candidates or postdocs who intend a career in academia).

Ethics

Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data

no code implementations18 Oct 2016 Decebal Constantin Mocanu, Maria Torres Vega, Eric Eaton, Peter Stone, Antonio Liotta

Conceived in the early 1990s, Experience Replay (ER) has been shown to be a successful mechanism to allow online learning algorithms to reuse past experiences.

reinforcement-learning Reinforcement Learning (RL)

Estimating 3D Trajectories from 2D Projections via Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machines

no code implementations20 Apr 2016 Decebal Constantin Mocanu, Haitham Bou Ammar, Luis Puig, Eric Eaton, Antonio Liotta

Estimation, recognition, and near-future prediction of 3D trajectories based on their two dimensional projections available from one camera source is an exceptionally difficult problem due to uncertainty in the trajectories and environment, high dimensionality of the specific trajectory states, lack of enough labeled data and so on.

Future prediction Time Series +1

Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret

no code implementations21 May 2015 Haitham Bou Ammar, Rasul Tutunov, Eric Eaton

Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.