Data to 7 Oct 2026

Safe Reinforcement Learning by Imagining the Near Future

arXiv 2202.07789 ↗First posted 15 Feb 2022cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. In this setting, a model-based agent with a sufficiently accurate model can avoid unsafe states. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstrate that our algorithm can achieve competitive rewards with fewer safety violations in several continuous control tasks.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

27 of 46 references.

References · 27

2014Adam: A Method for Stochastic Optimizationcited by 36,960
2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
2015Continuous control with deep reinforcement learningcited by 3,279
2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
2016Concrete Problems in AI Safetycited by 1,582
2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
2017Constrained Policy Optimizationcited by 928
2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
2018Reward Constrained Policy Optimizationcited by 397
2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302

15 more

2018Safe Exploration in Continuous Action Spacescited by 237
2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 156
2018Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guaranteescited by 138
2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
2020Conservative Safety Critics for Explorationcited by 107
2019Exploring Model-based Planning with Policy Networkscited by 90
2017Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learningcited by 86
2020Safe Reinforcement Learning via Curriculum Inductioncited by 73
2019Combating the Compounding-Error Problem with a Multi-step Modelcited by 52
2021Safe Continuous Control with Constrained Model-Based Policy Optimizationcited by 17
2016Learning from the Hindsight Plan -- Episodic MPC Improvementcited by 15
2020Accelerating Safe Reinforcement Learning with Constraint-mismatched Policiescited by 11
2020Provably Safe PAC-MDP Exploration Using Analogiescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 18; 2024: 16; 2025: 14; 2026: 5.

67 papers.

Sort:

By area:

2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
2023FLIRT: Feedback Loop In-context Red Teamingcited by 81
2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 76
2022Reachability Constrained Reinforcement Learningcited by 52
2023SafeDreamer: Safe Reinforcement Learning with World Modelscited by 50
2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
2022Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithmcited by 27
2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithmscited by 27
2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 20
2022Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificatecited by 16

38 more

2022Benchmarking Reinforcement Learning Techniques for Autonomous Navigationcited by 15
2022SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Controlcited by 15
2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 11
2022Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimizationcited by 10
2023Provably Safe Reinforcement Learning with Step-wise Violation Constraintscited by 10
2022LEADER: Learning Attention over Driving Behaviors for Planning under Uncertaintycited by 9
2023Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functionscited by 9
2025Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPscited by 8
2025SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfercited by 8
2022Provable Safe Reinforcement Learning with Binary Feedbackcited by 7
2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learningcited by 7
2026Safe Exploration via Policy Priorscited by 6
2023Learning for Edge-Weighted Online Bipartite Matching with Robustness Guaranteescited by 5
2023Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theorycited by 5
2023Anytime-Constrained Reinforcement Learningcited by 5
2024Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environmentscited by 5
2024Deterministic Policies for Constrained Reinforcement Learning in Polynomial Timecited by 5
2025Emergent Risk Awareness in Rational Agents under Resource Constraintscited by 5
2023Safe Reinforcement Learning with Dead-Ends Avoidance and Recoverycited by 4
2023Approximate Model-Based Shielding for Safe Reinforcement Learningcited by 4
2024Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimizationcited by 4
2024Predicting Future Actions of Reinforcement Learning Agentscited by 4
2022Safe Reinforcement Learning with Contrastive Risk Predictioncited by 3
2023Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanismcited by 3
2024Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approachcited by 3
2024Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuningcited by 3
2024A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safetycited by 3
2025Mutual Information Tracks Policy Coherence in Reinforcement Learningcited by 3
2023Approximate Shielding of Atari Agents for Safe Explorationcited by 2
2024Reinforcement Learning for Sustainable Energy: A Surveycited by 2
2025A Provable Approach for End-to-End Safe Reinforcement Learningcited by 2
2025Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regressioncited by 2
2022Guided Safe Shooting: model based reinforcement learning with safety constraintscited by 1
2023Modeling Risk in Reinforcement Learning: A Literature Mappingcited by 1
2024Policy Bifurcation in Safe Reinforcement Learningcited by 1
2024Preparing for Black Swans: The Antifragility Imperative for Machine Learningcited by 1
2024Provably Efficient Exploration in Inverse Constrained Reinforcement Learningcited by 1
2024Q-learning-based Model-free Safety Filtercited by 1

50 most cited of 67 All 67 (JSON)