The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.
Model-free safe reinforcement learning through neural barrier certificate
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PECTS learns dynamics and CBFs to constrain MPC trajectories probabilistically, enabling safer RL in stochastic unknown environments via sampling-based optimization.
citing papers explorer
-
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.
-
A Control Barrier Function-Constrained Model Predictive Control Framework for Safe Reinforcement Learning
PECTS learns dynamics and CBFs to constrain MPC trajectories probabilistically, enabling safer RL in stochastic unknown environments via sampling-based optimization.