| Safe Reinforcement Learning using Data-Driven Predictive Control | Nov 20, 2022 | continuous-controlContinuous Control | —Unverified | 0 |
| SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control | Nov 20, 2022 | reinforcement-learningReinforcement Learning | CodeCode Available | 0 |
| Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms | Oct 29, 2022 | Autonomous DrivingDiversity | CodeCode Available | 1 |
| Provable Safe Reinforcement Learning with Binary Feedback | Oct 26, 2022 | Active Learningreinforcement-learning | CodeCode Available | 1 |
| LMPriors: Pre-Trained Language Models as Task-Specific Priors | Oct 22, 2022 | Causal InferenceCommon Sense Reasoning | —Unverified | 0 |
| Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes | Oct 19, 2022 | reinforcement-learningReinforcement Learning | —Unverified | 0 |
| Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm | Oct 14, 2022 | Deep Reinforcement Learningreinforcement-learning | CodeCode Available | 1 |
| Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate | Oct 14, 2022 | Model-based Reinforcement Learningreinforcement-learning | CodeCode Available | 1 |
| Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation | Oct 2, 2022 | reinforcement-learningReinforcement Learning | CodeCode Available | 0 |
| Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments | Sep 29, 2022 | Reinforcement Learning (RL)Safe Reinforcement Learning | —Unverified | 0 |
