Search Results for author:
Found 40 papers, 14 papers with code
Can we hop in general? A discussion of benchmark selection and design using the Hopper environment
Empirical, benchmark-driven testing is a fundamental paradigm in the current RL community.
MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL
Our method, Model-Augmented Data for Temporal Difference learning (MAD-TD) uses small amounts of generated data to stabilize high UTD training and achieve competitive performance on the most challenging tasks in the DeepMind control suite.
Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation.
Neural Eulerian Scene Flow Fields
We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior.
Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models
In this work, we introduce the modality importance score (MIS) to identify such bias.
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video
Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead on coarse video labels indicating object presence.
Distributed Continual Learning
This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge.
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence
We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples by combatting value function divergence.
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
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.
A Metacognitive Approach to Out-of-Distribution Detection for Segmentation
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
We provide training and evaluation settings for assessing an agent's ability to learn compositional task policies.
CAROM Air -- Vehicle Localization and Traffic Scene Reconstruction from Aerial Videos
Road traffic scene reconstruction from videos has been desirable by road safety regulators, city planners, researchers, and autonomous driving technology developers.
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
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.
ZeroFlow: Scalable Scene Flow via Distillation
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds.
Ranked #2 on
Self-supervised Scene Flow Estimation
on Argoverse 2
(using extra training data)
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
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.
Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning
Satellite image analysis has important implications for land use, urbanization, and ecosystem monitoring.
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition
A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general understanding of the world.
CompoSuite: A Compositional Reinforcement Learning Benchmark
We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL).
Lifelong Inverse Reinforcement Learning
Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user.
Modular Lifelong Reinforcement Learning via Neural Composition
Empirically, we demonstrate that neural composition indeed captures the underlying structure of this space of problems.
SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries
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.
Gap Minimization for Knowledge Sharing and Transfer
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.
Prospective Learning: Principled Extrapolation to the Future
We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning.
Mako: Semi-supervised continual learning with minimal labeled data via data programming
This tool achieves similar performance, in terms of per-task accuracy and resistance to catastrophic forgetting, as compared to fully labeled data.
Towards a theory of out-of-distribution learning
Establishing proper and universally agreed-upon definitions for these learning setups is essential for thoroughly exploring the evolution of ideas across different learning scenarios and deriving generalized mathematical bounds for these learners.
Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems
Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse.
Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer
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
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.
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems.
Lifelong Learning of Factored Policies via Policy Gradients
Policy gradient methods have shown success in learning continuous control policies for high-dimensional dynamical systems.
Transfer Learning via Minimizing the Performance Gap Between Domains
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.
Zero-Shot Image Classification Using Coupled Dictionary Embedding
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes.
Artificial Intelligence for Pediatric Ophthalmology
KEYWORDS: pediatric ophthalmology, machine learning, artificial intelligence, deep learning
Tree-Structured Boosting: Connections Between Gradient Boosted Stumps and Full Decision Trees
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.
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
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.
Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience.
Blue Sky Ideas in Artificial Intelligence Education from the EAAI 2017 New and Future AI Educator Program
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).
Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data
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.
Estimating 3D Trajectories from 2D Projections via Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machines
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.
Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret
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.
