Results 101 to 110 of about 544,487 (316)

Generative Adversarial Imitation Learning [PDF]

open access: yesarXiv, 2016
Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement learning, then extract a policy from that cost function with reinforcement learning. This approach is indirect and can be slow.
arxiv  

3D (Bio) Printing Combined Fiber Fabrication Methods for Tissue Engineering Applications: Possibilities and Limitations

open access: yesAdvanced Functional Materials, EarlyView.
Biofabrication aims at providing innovative technologies and tools for the fabrication of tissue‐like constructs for tissue engineering and regenerative medicine applications. By integrating multiple biofabrication technologies, such as 3D (bio) printing with fiber fabrication methods, it would be more realistic to reconstruct native tissue's ...
Waseem Kitana   +2 more
wiley   +1 more source

Reinforcement Learning

open access: yes, 2019
Reinforcement Learning (RL) is one of the model free machine learning algorithms where the agent learns its behaviours from the environment by actually interacting with it. This is better than the offline planner because the agent actually interacts with the environment to learn its behaviours because it is almost impossible to simulate a real world in
Jimut Bahan Pal   +2 more
openaire   +2 more sources

Integration of Perovskite/Low‐Dimensional Material Heterostructures for Optoelectronics and Artificial Visual Systems

open access: yesAdvanced Functional Materials, EarlyView.
Heterojunctions combining halide perovskites with low‐dimensional materials enhance optoelectronic devices by enabling precise charge control and improving efficiency, stability, and speed. These synergies advance flexible electronics, wearable sensors, and neuromorphic computing, mimicking biological vision for real‐time image analysis and intelligent
Yu‐Jin Du   +11 more
wiley   +1 more source

Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning [PDF]

open access: yesarXiv, 2019
Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs efficient exploration; Evolutionary algorithms are stable, but with low sample efficiency; Imitation learning is both ...
arxiv  

One‐Shot Remote Integration of Macromolecular Synaptic Elements on a Chip for Ultrathin Flexible Neural Network System

open access: yesAdvanced Materials, EarlyView.
A novel one‐shot integration electropolymerization (OSIEP) method is developed as a breakthrough on the intricate photolithographic steps, enabling to compress all processes from synthesis to channel integration in one‐shot manufacturing. The specially designed dual bipolar electrodes provide the targeted depositions of poly(3,4‐ethylenedioxythiophene)
Jiyun Lee   +9 more
wiley   +1 more source

Pushing Radiative Cooling Technology to Real Applications

open access: yesAdvanced Materials, EarlyView.
Radiative cooling controls surface optical properties for solar and thermal radiation, offering solutions for global warming and energy savings. Despite significant advances, key challenges remain: optimizing optical efficiency, maintaining aesthetics, preventing overcooling, enhancing durability, and enabling scalable production.
Chongjia Lin   +8 more
wiley   +1 more source

Mutual Reinforcement Learning

open access: yes, 2021
Mutual learning is an emerging field in intelligent systems which takes inspiration from naturally intelligent agents and attempts to explore how agents can communicate and coop- erate to share information and learn more quickly. While agents in many biological systems have little trouble learning from one another, it is not immediately obvious how ...
openaire   +3 more sources

Differential effects of reward and punishment in decision making under uncertainty: a computational study.

open access: yesFrontiers in Neuroscience, 2014
Computational models of learning have proved largely successful in characterising potentialmechanisms which allow humans to make decisions in uncertain and volatile contexts.
Elaine eDuffin   +3 more
doaj   +1 more source

Home - About - Disclaimer - Privacy