Safe & Constrained RL

CAffNet: Hard Constraint-Affine Neural Networks

CAffNet embeds input-dependent affine constraints in a neural output layer. It guarantees feasibility for known nonempty constraint sets, but its combinatorial active-set cost and model-dependent safety assumptions remain central limitations.

CAffNet: Hard Constraint-Affine Neural Networks

The Safety–Information Deadlock in Adaptive Probabilistic Shielding

How online MDP estimation, interval uncertainty, and probabilistic shielding form a coupled loop in which blocking risky actions can also block the evidence needed to learn safety.

Hard Linear Constraints in Neural Decisions: Feasibility by Decision-Rule Anchoring

A critical note on enforcing input-dependent linear equality and inequality constraints in neural network outputs using a robustly feasible decision-rule anchor and minimal interpolation.

Enforcing hard linear constraints in deep learning models with decision rules

Lyapunov Projection for Continuous-Action Safe Reinforcement Learning

This note reads Lyapunov-based safe policy optimization as a practical projection bridge from finite CMDP safe policy iteration to continuous-action deep reinforcement learning, while separating exact CMDP guarantees from local approximation behavior.

Lyapunov-based Safe Policy Optimization for Continuous Control

Lyapunov-Based Safe Policy Improvement for CMDPs

Lyapunov constraints turn an expected cumulative safety budget in a CMDP into local restrictions on policy improvement. This note examines the exact certificate logic and the weaker status of neural approximations.

A lyapunov-based approach to safe reinforcement learning