Minimalistic attacks: How little it takes to fool deep reinforcement learning policies
Recent studies have revealed that neural-network-based policies can be easily fooled by
adversarial examples. However, while most prior works analyze the effects of perturbing …
adversarial examples. However, while most prior works analyze the effects of perturbing …
Matching-based capture-the-flag games for multi-agent systems
Competition and cooperation among agents in multiagent systems can be effectively
modeled as differential games. One of the typical tasks is capturing the flag, in which the …
modeled as differential games. One of the typical tasks is capturing the flag, in which the …
Enabling cognitive predictive maintenance using machine learning: Approaches and design methodologies
V Poosapati, V Katneni, VK Manda… - Soft Computing and …, 2019 - Springer
Asset reliability and 100% availability of machines are a competitive business advantage in
complex industrial environment as they play a vital role in improving productivity. Preventive …
complex industrial environment as they play a vital role in improving productivity. Preventive …
A developmental evolutionary learning framework for robotic chinese stroke writing
The ability of robots to write Chinese strokes, which is recognized as a sophisticated task,
involves complicated kinematic control algorithms. The conventional approaches for robotic …
involves complicated kinematic control algorithms. The conventional approaches for robotic …
Robotic-assisted rehabilitation trainer improves balance function in stroke survivors
Nerve injury after stroke leads to disorders of locomotion and a declining balance function,
which increases the risk of falling. Restriction of pelvic motions can hinder successful …
which increases the risk of falling. Restriction of pelvic motions can hinder successful …
Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured Environments
C Wang, L Yang, Z Lin, Y Liao, G Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Assembling a slave object into a fixture-free master object represents a critical challenge in
flexible manufacturing. Existing deep reinforcement learning-based methods, while …
flexible manufacturing. Existing deep reinforcement learning-based methods, while …
A partially observable Markov-decision-process-based blackboard architecture for cognitive agents in partially observable environments
H Itoh, H Nakano, R Tokushima… - … on Cognitive and …, 2020 - ieeexplore.ieee.org
Partial observability, or the inability of an agent to fully observe the state of its environment,
exists in many real-world problem domains. However, most cognitive architectures do not …
exists in many real-world problem domains. However, most cognitive architectures do not …
Modeling reverse thinking for machine learning
H Li, G Wen - Soft Computing, 2020 - Springer
Human inertial thinking schemes can be formed through learning, which are then applied to
quickly solve similar problems later. However, when problems are significantly different …
quickly solve similar problems later. However, when problems are significantly different …
Metaphorical-Enactive: Al-Ghazali's Education Media on Sufism Themes
This study aimed to explore and discuss the educational media used by Al-Ghazali relevant
to essential concepts in Sufism. The role of the qalb in Sufism is very urgent in human life …
to essential concepts in Sufism. The role of the qalb in Sufism is very urgent in human life …
On Cognitive Searching Optimization in Semi‐Markov Jump Decision Using Multistep Transition and Mental Rehearsal
B Ren, T Yin, S Fu - Complexity, 2021 - Wiley Online Library
Cognitive searching optimization is a subconscious mental phenomenon in decision
making. Aroused by exploiting accessible human action, alleviating inefficient decision and …
making. Aroused by exploiting accessible human action, alleviating inefficient decision and …