21 accepted papers
Reinforcement learning (RL) has achieved impressive results across various domains, yet the resulting policies often fail to generalize beyond the specific tasks encountered during training. This lack of robustness limits their deployment in real-world scenarios where diverse and unpredictable task …
There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both classical and modern reinforcement learning (RL). By contra…
Neural radiance fields (NeRF)-based methods with multi-resolution hash encoding enable efficient sparse-view CBCT reconstruction, but real-world projections violate ideal assumptions due to scatter/noise and related inconsistencies. Uniformly fusing hash-grid levels entangles heterogeneous frequency
The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as primal-dual ordinary differential equation (ODE) dynamics sub
Offline reinforcement learning (RL) aims to learn a policy from a fixed dataset without additional environment interaction. However, effective offline policy learning often requires a large and diverse dataset to mitigate epistemic uncertainty. Collecting such data demands substantial online interac…
Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the first layer can lead to feature learning; characterized by…
Large scale active exploration has recently revealed limitations of visual SLAM’s tracking ability. Active view planning methods based on reinforcement learning have been proposed to improve visual tracking robustness.In this work, we expose the limitations of deep reinforcement learning-based visua…
Q-learning is widely used algorithm in reinforcement learning (RL) community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This paper develops a new Q-learning algorithm, called RegQ, t…
This paper tackles a localization problem in large-scale indoor environments with wayfinding maps. A wayfinding map abstractly portrays the environment, and humans can localize themselves based on the map. However, when it comes to using it for robot localization, large geometrical discrepancies bet…
Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence issue when the off-policy scheme is used together with linear f…
Evaluating the performance of machine learning models under distribution shifts is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain. Recent work suggests that the notion of *disagreement*, the degree…
We present a new pipeline for acquiring a textured mesh in the wild with a single smartphone which offers access to images, depth maps, and valid poses. Our method first introduces an RGBD-aided structure from motion, which can yield filtered depth maps and refines camera poses guided by correspondi…
Global registration using 3D point clouds is a crucial technology for mobile platforms to achieve localization or manage loop-closing situations. In recent years, numerous researchers have proposed global registration methods to address a large number of outlier correspondences. Unfortunately, the d…
In modern machine learning, users often have to collaborate to learn distributions that generate the data. Communication can be a significant bottleneck. Prior work has studied homogeneous users---i.e., whose data follow the same discrete distribution---and has provided optimal communication-effici…
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metric…
We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e.g., a department store or a metro station. Our approach predicts absolute scale depth maps over the entire scene consisting of a static background and multiple movi…
Estimating the precise location of a camera using visual localization enables interesting applications such as augmented reality or robot navigation. This is particularly useful in indoor environments where other localization technologies, such as GNSS, fail. Indoor spaces impose interesting challen…
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth labels. Our self-supervised algorithm is designed for challengi…
This paper develops a novel and unified framework to analyze the convergence of a large family of Q-learning algorithms from the switching system perspective. We show that the nonlinear ODE models associated with Q-learning and many of its variants can be naturally formulated as affine switchin…
With its essential role in achieving full autonomy of robot navigation, place recognition has been widely studied with various approaches. Recently, numerous point cloud-based methods with deep learning implementation have been proposed with promising results for their application in outdoor environ…
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms that maintain two separate l…