Results 41 to 50 of about 2,271,128 (293)

Revisiting Safe Exploration in Safe Reinforcement learning

CoRR
Safe reinforcement learning (SafeRL) extends standard reinforcement learning with the idea of safety, where safety is typically defined through the constraint of the expected cost return of a trajectory being below a set limit. However, this metric fails to distinguish how costs accrue, treating infrequent severe cost events as equal to frequent mild ...
David Eckel, Baohe Zhang, Joschka Bödecker   +2 more
openaire   +2 more sources

Decoupled Learning of Environment Characteristics for Safe Exploration

CoRR, 2017
Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task. This makes it harder to transfer skills between tasks in the same environment.
Van Molle, Pieter, Verbelen, Tim, Bohez, Steven, Leroux, Sam, Simoens, Pieter, Dhoedt, Bart   +5 more
openaire   +4 more sources

Approximate Shielding of Atari Agents for Safe Exploration

CoRR, 2023
Accepted for presentation at the ALA workshop as part of AAMAS ...
Alexander W. Goodall, Francesco Belardinelli   +1 more
openaire   +3 more sources

Kansas Safe Kids Annual Report

, 2020
Safe Kids Kansas is a 501c(3) charitable organization and is a member of Safe Kids Worldwide, a global organization dedicated to preventing injuries in children.
Safe Kids Kansas, Inc.
core   +1 more source

Deep Reinforcement Learning-Based Failure-Safe Motion Planning for a 4-Wheeled 2-Steering Lunar Rover

Aerospace, 2023
The growing trend of onboard computational autonomy has increased the need for self-reliant rovers (SRRs) with high efficiency for unmanned rover activities.
Beom-Joon Park, Hyun-Joon Chung
doaj   +1 more source

Safe Exploration by Solving Early Terminated MDP

CoRR, 2021
Safe exploration is crucial for the real-world application of reinforcement learning (RL). Previous works consider the safe exploration problem as Constrained Markov Decision Process (CMDP), where the policies are being optimized under constraints. However, when encountering any potential dangers, human tends to stop immediately and rarely learns to ...
Hao Sun, Ziping Xu, Meng Fang, Zhenghao Peng, Jiadong Guo, Bo Dai 0002, Bolei Zhou   +6 more
openaire   +2 more sources

Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear Markov Decision Processes

IEEE Open Journal of Control Systems
We study data-driven computation of probabilistic controlled invariant sets (PCIS) for safety-critical reinforcement learning under unknown dynamics. Assuming a linear MDP model, we use regularized least squares and self-normalized confidence bounds to ...
Kazumune Hashimoto, Shunki Kimura, Junya Ikemoto, Kazunobu Serizawa, Yulong Gao, Kai Cai   +5 more
doaj   +1 more source

Safe Stochastic Explorer: Enabling Safe Goal Driven Exploration in Stochastic Environments and Safe Interaction with Unknown Objects

CoRR
Autonomous robots operating in unstructured, safety-critical environments, from planetary exploration to warehouses and homes, must learn to safely navigate and interact with their surroundings despite limited prior knowledge. Current methods for safe control, such as Hamilton-Jacobi Reachability and Control Barrier Functions, assume known system ...
Nikhil Uday Shinde, Dylan Hirsch, Michael C. Yip, Sylvia L. Herbert   +3 more
openaire   +3 more sources

Indoor Visual Exploration with Multi-Rotor Aerial Robotic Vehicles

Sensors, 2022
In this work, we develop a reactive algorithm for autonomous exploration of indoor, unknown environments for multiple autonomous multi-rotor robots. The novelty of our approach rests on a two-level control architecture comprised of an Artificial-Harmonic
Panagiotis Rousseas, George C. Karras, Charalampos P. Bechlioulis, Kostas J. Kyriakopoulos   +3 more
doaj   +1 more source

Solid Pseudopapillary Neoplasm of the Pancreas in Children and Adolescents: Expert Recommendations

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Solid pseudopapillary neoplasm of the pancreas (SPN) is a rare low‐grade malignant exocrine pancreatic tumor, mostly discovered during the second decade of life in females, with a very good prognosis, provided microscopically complete surgical excision is achieved.
Sabine Irtan, Michael Abele, Calogero Virgone, Michaela Kuhlen, Ricardo Lopez‐Almarez, Tal Ben‐Ami, Ewa Bien, Maja Cesen, Malgorzata A. Krawczyk, Andrea Ferrari, Gianni Bisogno, Yves Reguerre, Dominik T. Schneider, Louise Galmiche, Jorg Fuchs, Sarah Braungart, Bilgehan Yalcin, Ines B. Brecht, Daniel Orbach   +18 more
wiley   +1 more source