Provably Optimal Reinforcement Learning under Safety Filtering

arXiv:2510.18082 · cs.LG, cs.RO, cs.SY, eess.SY · Submitted 2025-10-20 · Read on arXiv

cs.LG, cs.RO, cs.SY, eess.SY

Submitted: 2025-10-20

Updated: 2026-09-17

Comments: Proceedings of the Second International Association for Safe and Ethical AI Conference (IASEAI'26); 17 pages, 3 figures

Journal ref: Proceedings of IASEAI Conference 2(1), 488-500 (2026)

DOI: 10.1609/iaseai.v2i1.43046

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

Terminology

• Reinforcement Learning — 38× in this paper · explained in 4 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Actor — 8× in this paper · explained in 3 episodes
• IEEE Conference on Decision and Control — 5× in this paper
• Constrained Policy Optimization — 4× in this paper
• Action Space — 3× in this paper · explained in 1 episode
• Q-learning — 3× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 3× in this paper · explained in 25 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Sample Efficiency — 3× in this paper · explained in 4 episodes
• Convergence Guarantees — 2× in this paper · explained in 3 episodes
• International Conference on Robotics and Automation — 2× in this paper
• Abstraction — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Hybrid System — 1× in this paper · explained in 2 episodes
• Model Predictive Control (MPC) — 1× in this paper · explained in 5 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Standardized Metrics — 1× in this paper · explained in 3 episodes

Sources

• Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning
• Reward Constrained Policy Optimization
• Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks