Safe rlhf: Safe reinforcement learning from human feedback
With the development of large language models (LLMs), striking a balance between the
performance and safety of AI systems has never been more critical. However, the inherent …
performance and safety of AI systems has never been more critical. However, the inherent …
Is sora a world simulator? a comprehensive survey on general world models and beyond
General world models represent a crucial pathway toward achieving Artificial General
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …
World models for autonomous driving: An initial survey
In the rapidly evolving landscape of autonomous driving, the capability to accurately predict
future events and assess their implications is paramount for both safety and efficiency …
future events and assess their implications is paramount for both safety and efficiency …
Robust Training of Federated Models with Extremely Label Deficiency
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for
collaboratively training machine learning models using distributed data with label deficiency …
collaboratively training machine learning models using distributed data with label deficiency …
Feasibility Consistent Representation Learning for Safe Reinforcement Learning
In the field of safe reinforcement learning (RL), finding a balance between satisfying safety
constraints and optimizing reward performance presents a significant challenge. A key …
constraints and optimizing reward performance presents a significant challenge. A key …
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using
a pre-collected dataset. Most current methods struggle with the mismatch between imperfect …
a pre-collected dataset. Most current methods struggle with the mismatch between imperfect …
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
Among approaches for provably safe reinforcement learning, Model Predictive Shielding
(MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces …
(MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces …
FOSP: Fine-tuning Offline Safe Policy through World Models
Model-based Reinforcement Learning (RL) has shown its high training efficiency and
capability of handling high-dimensional tasks. Regarding safety issues, safe model-based …
capability of handling high-dimensional tasks. Regarding safety issues, safe model-based …
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
AW Goodall, F Belardinelli - arXiv preprint arXiv:2402.00816, 2024 - arxiv.org
Shielding is a popular technique for achieving safe reinforcement learning (RL). However,
classical shielding approaches come with quite restrictive assumptions making them difficult …
classical shielding approaches come with quite restrictive assumptions making them difficult …
[PDF][PDF] Evaluation of DreamerV3 for defective plant search in a simulated crop
T Bonte - 1924 - edepot.wur.nl
The use of autonomous robots is increasing in agriculture; however, their development is
still slow as each task usually needs a specific hard-coded behaviour. Hard coding of all …
still slow as each task usually needs a specific hard-coded behaviour. Hard coding of all …