This repo lists most recent papers with their code in safe RL, some papers without available code are not included. Welcome to change this list if additional documents found.
-
Conservative Exploration in Reinforcement Learning, International Conference on Artificial Intelligence and Statistics 2020
-
Projection-based Constrained Policy Optimization (PCPO), 2020 ICLR, no code.
-
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies, 2021 ICML, code
-
A Lyapunov-based Approach to Safe Reinforcement Learning, 2018 Nips code
-
Provably efficient safe exploration via primal-dual policy optimization, 2021 ICML, no code, slide
-
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks, 2021 arxiv, code
-
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations, 2021 arxiv, no code
-
Safe Reinforcement Learning Using Advantage-Based Intervention, 2021 ICML, code
-
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones, 2021 IEEE ROBOTICS AND AUTOMATION LETTERS, code
-
Safe Reinforcement Learning via Curriculum Induction, 2020 Nips, code
-
AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training, 2021 AAMAS, code
-
Safe Reinforcement Learning in Constrained Markov Decision Processes, 2020 ICML, code, slide
-
A Safe and Fast Reinforcement Learning Safety Layer for Continuous, 2021 IEEE Robotics and Automation Letters, code
-
Safe Exploration in Continuous Action Spaces, 2018 IEEE CDC, code
-
Conservative Agency via Attainable Utility Preservation, 2020 AAAI AES, code
-
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee, 2021 ICML, no code
-
Control Regularization for Reduced Variance Reinforcement Learning. 2019 ICML, matlab code
-
Batch Policy Learning under Constraints, 2020 ICML, code
-
Safe Exploration for Interactive Machine Learning, 2019 Nips, no code
-
Density Constrained Reinforcement Learning, 2021 ICML, no code
-
Inverse Constrained Reinforcement Learning, 2021 ICML, code
-
Glas: Global-to-local safe autonomy synthesis for multi-robot motion planning with end-to-end learning, 2020 IEEE Robotics and Automation Letters, code
-
Constrained Markov Decision Processes via Backward Value Functions, 2020 ICML, code
- Actor-Critic Reinforcement Learning for Control With Stability Guarantee, 2020 IEEE ROBOTICS AND AUTOMATION LETTERS, code
- Safe Planning via Model Predictive Shielding, 2019 ACC, code
- Responsive Safety in Reinforcement Learning by PID Lagrangian Methods, 2020 ICML, code
- IPO: Interior-Point Policy Optimization under Constraints, 2020 AAAI, no code
-
Constrained Policy Optimization, 2017 ICML, code
-
Enforcing robust control guarantees within neural network policies, 2021 ICML, code
-
Constrained Cross-Entropy Method for Safe Reinforcement Learning, 2018 Nips, code
-
Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method, 2020 arxiv, code
-
End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks, 2019 AAAI, Code
-
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria, 2017 arxiv, no code
-
Convergent Policy Optimization for Safe Reinforcement Learning, 2019 Nips, code
-
Lyapunov-based Safe Policy Optimization for Continuous Control
-
CAQL: CONTINUOUS ACTION Q-LEARNING, 2020 ICLR, no code
- Safe Model-based Reinforcement Learning with Stability Guarantees
- The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
- Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processes, 2017 CDC
- Code
- Safe reinforcement learning using risk mapping by similarity
- Autonomous navigation via deep reinforcement learning for resource constraint edge nodes using transfer learning
- [Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks]
- Deep reinforcement learning with reference system to handle constraints for energy-efficient train control
- Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints
- Deep-Reinforcement-Learning-Based Capacity Scheduling for PV-Battery Storage System
- Multi-Agent Safe Policy Learning for Power Management of Networked Microgrids
- Constrained EV Charging Scheduling Based on Safe Deep Reinforcement Learning
- Constrained Dual-Level Bandit for Personalized Impression Regulation in Online Ranking Systems
- Estimating and Penalizing Preference Shift in Recommender Systems
- Short-term wind speed forecasting using deep reinforcement learning with improved multiple error correction approach
- An Improved Reinforcement Learning for Security-Constrained Economic Dispatch of Battery Energy Storage in Microgrids
- Safe Reinforcement Learning for Emergency LoadShedding of Power Systems
- Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems
- Safe reinforcement learning-based resilient proactive scheduling for a commercial building considering correlated demand response
- A Learning-based Optimal Market Bidding Strategy for Price-Maker Energy Storage
- Energy-Efficient Secure Video Streaming in UAV-Enabled Wireless Networks: A Safe-DQN Approach
- Trajectory Optimization for UAV Emergency Communication with Limited User Equipment Energy: A safe-DQN Approach
- Optimal energy management strategies for energy Internet via deep reinforcement learning approach
-
Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach
-
Context-Aware Safe Reinforcement Learning for Non-Stationary Environments, 2021 arxiv, no code, meta-learning
-
Learning to be Safe: Deep RL with a Safety Critic, 2020 arxiv, no code, transfer learning
-
Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning, no code, arxiv
-
REINFORCEMENT LEARNING WITH SAFE EXPLORATION FOR NETWORK SECURITY, no code
-
Continuous Safe Learning Based on First Principles and Constraints for Autonomous Driving, no code
-
UAV-aided cellular communications with deep reinforcement learning against jamming, no code
-
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences, ICML 2020, code
-
Safe policy improvement with baseline bootstrapping, ICML 2019
-
Safe policy improvement with baseline bootstrapping in factored environments, aaai 2020
- A Comprehensive Survey on Safe Reinforcement Learning
- Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning, 2021, code
- Sui, Y., Gotovos, A., Burdick, J. W., and Krause, A. Safe exploration for optimization with Gaussian processes. In International Conference on Machine Learning (ICML), 2015.
- Turchetta, M., Berkenkamp, F., and Krause, A. Safe exploration in finite Markov decision processes with Gaussian processes. In Neural Information Processing Systems (NeurIPS), 2016. code
- Wachi et al. "Safe Exploration and Optimization of Constrained MDPs using Gaussian Processes." AAAI 2018. no code
- S. Bansal, M. Chen, S. Herbert, and C. J. Tomlin, “Hamilton-jacobi reachability: A brief overview and recent advances”, in Conference on Decision and Control (CDC), 2017.
- S. Li and O. Bastani, “Robust model predictive shielding for safe reinforcement learning with stochastic dynamics”, in Proc. IEEE Int. Conf. Robotics and Automation (ICRA), 2020.
- J. F. Fisac, A. K. Akametalu, M. N. Zeilinger, S. Kaynama, J. Gillula, and C. J. Tomlin, “A general safety framework for learningbased control in uncertain robotic systems”, in IEEE Transactions on Automatic Control, 2018.
- J. H. Gillula and C. J. Tomlin, “Guaranteed safe online learning via reachability: Tracking a ground target using a quadrotor”, in Proc. IEEE Int. Conf. Robotics and Automation (ICRA), 2012.
- E. Altman, Constrained Markov Decision Processes.1999, p. 260.