A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Graph-based state representation improves deep RL performance.
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability. We utilize the variational intrinsic control framework (Gregor et.al., 2016) which maximizes empowerment -- the ability to reliably reach a diverse set of states and show how to ide…
The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck states. This work adopts a complementary approach, where we attempt to discover option…
Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberat…
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions di…
A new algorithm finds optimal solutions for constrained decision processes.
Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and identities from face dataset. However, most of these studies focus on supervise…
This paper improves MADDPG's performance in discrete grid-world scenarios.
Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be stored in the forms of features, individual models, and the average model, each lying at a different granularity. However, new tasks may requi…
Machine learning has shown growing success in recent years. However, current machine learning systems are highly specialized, trained for particular problems or domains, and typically on a single narrow dataset. Human learning, on the other hand, is highly general and adaptable. Never-ending learning is a machine learn…
Improves RL planning by proposing sub-goals hierarchically.
Paper tackles reinforcement learning generalization through invariant policy optimization.
The paper introduces MDP homomorphic networks for faster reinforcement learning.
Introduces a natural parallel translation for navigation data.
We designed a grid world task to study human planning and re-planning behavior in an unknown stochastic environment. In our grid world, participants were asked to travel from a random starting point to a random goal position while maximizing their reward. Because they were not familiar with the environment, they needed…
Challenge to separate Earth's magnetic field from vehicle's magnetic field for accurate navigation.
Navigation in Lorentz Finsler geometry induces isoparametric hypersurfaces.
The paper solves navigation problems on conic Kropina manifolds and establishes curvature relationships.
Robotic navigation improves with RL and ultrasound images.
Improved robot navigation using multi-head attention for natural language instructions.
The problem of pursuing a moving target is always one of the main topics in navigation. In the literatures, there are two well-known algorithms called Pure Pursuit and Pure Rendezvous navigation in the 3-dimensional space . In this paper, these two methods are combined to introduce a novel family of pursu…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…
SLAM-net learns to navigate visually in challenging indoor environments.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
Bayesian model for energy consumption helps electric vehicles navigate efficiently.
This work analyzes minimum-time navigation on Riemannian manifolds using Finsler geometry.
A new RL model ensures safe learning in uncertain environments.
Deep learning agent improves pedestrian navigation in urban environments.
Bayesian model for energy-efficient EV navigation.
Solves time-minimizing navigation on a mountain slope using Riemann-Finsler geometry.
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.
New algorithms solve time-dependent navigation problems, including zig-zag paths.
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation…
OtoWorld helps agents learn to navigate by listening in interactive environments.
We consider a setting in which the objective is to learn to navigate in a controlled Markov process (CMP) where transition probabilities may abruptly change. For this setting, we propose a performance measure called exploration steps which counts the time steps at which the learner lacks sufficient knowledge to navigat…
Curiosity-Critic improves world model training by focusing on cumulative prediction error.
UAV uses RL to navigate, map, and detect targets in unknown environments.
In this paper, we study Zermelo navigation on Riemannian manifolds and use that to solve a long standing problem in Finsler geometry. Namely, the complete classification of strongly convex Randers metrics of constant flag curvature.
This research introduces an autonomous robot navigation method using reinforcement learning.
Agents learn to communicate and solve navigation tasks efficiently.
We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to n…
Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often operate in a generic, user-agnostic manner. However, to minimize confusion and navigation …
New method identifies critical states to improve RL agent explainability and speed.
Study optimal paths in Zermelo's navigation problem using geometric equations.
H-STGCN predicts traffic using navigation data and improves accuracy.
The present paper studies globally defined Kropina metrics as solutions of the Zermelo's navigation problem. Moreover, we characterize the Kropina metrics of constant flag curvature showing that up to local isometry, there are only two model spaces of them: the Euclidean space and the odd-dimensional spheres.