arXiv research

Proposes a method to improve few-shot transfer in off-dynamics RL.

The paper shows how to learn causal representations with few environments and finite samples.

Study on estimating causal effects with limited data and multiple environments.

Before deploying autonomous agents in the real world, we need to be confident they will perform safely in novel situations. Ideally, we would expose agents to a very wide range of situations during training, allowing them to learn about every possible danger, but this is often impractical. This paper investigates safet…

Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable…

Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…

AdaRL adapts quickly to new environments with minimal data.

Meta-learner infers subtask graph to adapt quickly to unknown tasks.

New online few-shot learning model for context-aware recognition.

Paper introduces effect-invariance for better policy generalization.

New algorithm guarantees domain generalization with few environments.

OPSRL algorithm reduces regret with few samples in reinforcement learning.

Meta learning improves with contextualizers that adapt to examples.

Graph Prototypical Networks improve few-shot node classification on attributed networks.

New RL method learns value function for many policies using few key states.

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for some environments, they can also lead to sub-optimal behavior in others. Secondl…

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully observable environments. In this paper, we generalize a variety of these advances to part…

SPARTAN learns sparse interaction graphs between objects in scenes.

Introduces Conditional Action Trees to simplify RL action spaces.

Unified framework explains few-shot multimodal medical imaging performance.

Bayesian optimization has emerged as a strong candidate tool for global optimization of functions with expensive evaluation costs. However, due to the dynamic nature of research in Bayesian approaches, and the evolution of computing technology, using Bayesian optimization in a parallel computing environment remains a c…

Novel framework for data sharing and coordinated exploration in concurrent RL with non-identical environments.

Novel radar waveform design for autonomous vehicles.

We consider the exploration problem: an agent equipped with a depth sensor must map out a previously unknown environment using as few sensor measurements as possible. We propose an approach based on supervised learning of a greedy algorithm. We provide a bound on the optimality of the greedy algorithm using submodulari…

Decentralized learning for matching markets with time-varying preferences.

In prior research, a statistically cheap method was developed to monitor transportation network performance by using only a few groups of agents without having to forecast the population flows. The current study validates this "multi-agent inverse optimization" method using taxi GPS probe data from the city of Wuhan, C…

New mirror maps improve PMD performance in reinforcement learning.

NeRF-VAE generates 3D scenes with geometric structure from few images.

Novel LSTM network predicts pulsar timing residuals with few-shot data.

Few-shot learning improves bearing fault diagnosis with limited data.

This paper reviews FSL for open-world learning, addressing uncertainties and dynamic conditions.

Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous n…

New method improves reinforcement learning generalization.

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed bandit models with arms in an exponential family) reveal that the sample complexity …

Image modality recognition is essential for efficient imaging workflows in current clinical environments, where multiple imaging modalities are used to better comprehend complex diseases. Emerging biomarkers from novel, rare modalities are being developed to aid in such understanding, however the availability of these …

Recently, large-scale cascading failures in complex systems have garnered substantial attention. Such extreme events have been treated as an integral part of the self-organized criticality (SOC). Recent empirical work has suggested that some extreme events systematically deviate from the SOC paradigm, requiring a diffe…

In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the…

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning,…

Neural production systems learn visual dynamics by applying rule templates to entities.

This paper presents a framework for estimating the remaining useful life (RUL) of mechanical systems. The framework consists of a multi-layer perceptron and an evolutionary algorithm for optimizing the data-related parameters. The framework makes use of a strided time window to estimate the RUL for mechanical component…

ICON-OCnet solves optimal execution problems with neural networks and few examples.

Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes. We propose Recurrent Independent Mechanisms (RIMs), a new recurrent architecture in which multiple groups of recurrent cells operate wit…

DSAC improves robustness of imitation learning.

New method interprets complex models for music and urban simulations.

VMGP extends Gaussian processes for Bayesian meta-learning, improving uncertainty prediction.

FORK improves model-free reinforcement learning performance.

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for dri…

Proposes DLGPD model to learn dynamics from images for planning.