Видео с ютуба Safe Rl

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones (ICRA 2021 Talk)

Безопасное и справедливое обучение с подкреплением

RLSS 2023 - Safe Reinforcement Learning - Felix Berkenkamp

Safe Reinforcement Learning Example

RL (of Next) - Safe With Me

SAVED: Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Наташа Жак - Многоагентное обучение с подкреплением для доказуемо надежной безопасности LLM [Семи...

Exploration Hacking: Can LLMs learn to resist RL training? - Joschka Braun

Webinar: Quantum-safe IPsec, a hands-on technical guide

Safe Reinforcement Learning on a Real Robot!

Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk

RSS 2021, Spotlight Talk 11: Safe Reinforcement Learning via Statistical Model Predictive Shielding

Regularization in RL, Why RL Generalizes, and Why SFT Forgets | RLHF & Post-training Book Lecture 10

Безопасность ИИ, RLHF и самообучение — Джаред Каплан | Стэнфордская магистерская программа по сис...

Bridging Model-based Safety and Mode-free RL through System Identification of Linear Models

Обеспечение безопасности в онлайн-обучении с подкреплением за счет использования офлайн-данных

Safety Filtering While Training: Improving the Performance and Sample Efficiency of RL Agents

Семинар 8. Иерархические и методы на основе модели мира для Safe RL