Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/SvenGronauer/Bullet-Safety-Gym

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Exploration by Random Network Distillation
• Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation
• PaLM-E: An Embodied Multimodal Language Model
• MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
• VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
• OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research
• VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving
• Updating Robot Safety Representations Online from Natural Language Feedback
• Proximal Policy Optimization Algorithms
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
• Penalized Proximal Policy Optimization for Safe Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks