BIASVARIANCE_IR Telegram 405
بدلیل اینکه از یادگیری تقویتی در موقعیت‌های حساس ممکن است استفاده شود، یکی از نیازهایی که لازم است در نظر گرفته شود، امنیت عامل‌های مبتنی‌بر تقویتی است. اخیرا مقاله‌ی جدید در این زمینه با نام SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents در آرکایو آپلود شده که به این زمینه پرداخته است؛ همچنین، ارجاعات این مقاله نیز می‌توانند بسیار کمک‌کننده باشند. این حوزه را برای ارایه‌ی مقاله پیشنهاد می‌دهیم.

Deep reinforcement learning algorithms (DRL) are increasingly being used in safety-critical systems. Ensuring the safety of DRL agents is a critical concern in such contexts. However, relying solely on testing is not sufficient to ensure safety as it does not offer guarantees. Building safety monitors is one solution to alleviate this challenge. This paper proposes SMARLA, a machine learning-based safety monitoring approach designed for DRL agents. For practical reasons, SMARLA is designed to be black-box (as it does not require access to the internals of the agent) and leverages state abstraction to reduce the state space and thus facilitate the learning of safety violation prediction models from agent’s states. We validated SMARLA on two well-known RL case studies. Empirical analysis reveals that SMARLA achieves accurate violation prediction with a low false positive rate, and can predict safety violations at an early stage, approximately halfway through the agent’s execution before violations occur.

ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
#یادگیری_عمیق #شبکه_عصبی #معرفی_مقاله #یادگیری_تقویتی_عمیق #یادگیری_تقویتی
ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
پشتیبانی | کانال | سایت | اینستاگرام | آپارات



tgoop.com/biasvariance_ir/405
Create:
Last Update:

بدلیل اینکه از یادگیری تقویتی در موقعیت‌های حساس ممکن است استفاده شود، یکی از نیازهایی که لازم است در نظر گرفته شود، امنیت عامل‌های مبتنی‌بر تقویتی است. اخیرا مقاله‌ی جدید در این زمینه با نام SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents در آرکایو آپلود شده که به این زمینه پرداخته است؛ همچنین، ارجاعات این مقاله نیز می‌توانند بسیار کمک‌کننده باشند. این حوزه را برای ارایه‌ی مقاله پیشنهاد می‌دهیم.

Deep reinforcement learning algorithms (DRL) are increasingly being used in safety-critical systems. Ensuring the safety of DRL agents is a critical concern in such contexts. However, relying solely on testing is not sufficient to ensure safety as it does not offer guarantees. Building safety monitors is one solution to alleviate this challenge. This paper proposes SMARLA, a machine learning-based safety monitoring approach designed for DRL agents. For practical reasons, SMARLA is designed to be black-box (as it does not require access to the internals of the agent) and leverages state abstraction to reduce the state space and thus facilitate the learning of safety violation prediction models from agent’s states. We validated SMARLA on two well-known RL case studies. Empirical analysis reveals that SMARLA achieves accurate violation prediction with a low false positive rate, and can predict safety violations at an early stage, approximately halfway through the agent’s execution before violations occur.

ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
#یادگیری_عمیق #شبکه_عصبی #معرفی_مقاله #یادگیری_تقویتی_عمیق #یادگیری_تقویتی
ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
پشتیبانی | کانال | سایت | اینستاگرام | آپارات

BY Bias Variance


Share with your friend now:
tgoop.com/biasvariance_ir/405

View MORE
Open in Telegram


Telegram News

Date: |

Private channels are only accessible to subscribers and don’t appear in public searches. To join a private channel, you need to receive a link from the owner (administrator). A private channel is an excellent solution for companies and teams. You can also use this type of channel to write down personal notes, reflections, etc. By the way, you can make your private channel public at any moment. Write your hashtags in the language of your target audience. Activate up to 20 bots Users are more open to new information on workdays rather than weekends. Each account can create up to 10 public channels
from us


Telegram Bias Variance
FROM American