{"total":337,"rows":[{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91,"area":"offlinerl"},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"area":null},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"area":null},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59,"area":null},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49,"area":"alignment"},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2206.04436","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","created":"2022-06-09","cited_by_count":41,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37,"area":"alignment"},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2105.10682","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","created":"2021-05-22","cited_by_count":30,"area":null},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2111.07695","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","created":"2021-11-15","cited_by_count":27,"area":null},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2210.05650","title":"Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2022-10-11","cited_by_count":26,"area":null},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2206.02678","title":"Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path","created":"2022-06-06","cited_by_count":22,"area":null},{"id":"2112.13414","title":"Reinforcement Learning with Dynamic Convex Risk Measures","created":"2021-12-26","cited_by_count":21,"area":null},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2108.13680","title":"Learning Practically Feasible Policies for Online 3D Bin Packing","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2210.07553","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2304.12477","title":"On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes","created":"2023-04-24","cited_by_count":18,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2104.06922","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","created":"2021-04-14","cited_by_count":17,"area":null},{"id":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17,"area":null},{"id":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17,"area":null},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"1808.04468","title":"Risk-Sensitive Generative Adversarial Imitation Learning","created":"2018-08-13","cited_by_count":16,"area":"offlinerl"},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16,"area":"deeprl"},{"id":"2102.11075","title":"SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2108.11623","title":"Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian","created":"2021-08-26","cited_by_count":15,"area":null},{"id":"2301.12601","title":"Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents","created":"2023-01-30","cited_by_count":15,"area":null},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"area":"deeprl"},{"id":"2210.12546","title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","created":"2022-10-22","cited_by_count":14,"area":null},{"id":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2102.08539","title":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","created":"2021-02-17","cited_by_count":13,"area":null},{"id":"2505.17342","title":"A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2103.09230","title":"Lyapunov Barrier Policy Optimization","created":"2021-03-16","cited_by_count":12,"area":null},{"id":"2107.11722","title":"Learning Risk-aware Costmaps for Traversability in Challenging Environments","created":"2021-07-25","cited_by_count":12,"area":null},{"id":"2206.05240","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2307.08873","title":"An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2504.19139","title":"Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments","created":"2025-04-27","cited_by_count":12,"area":null},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2306.17279","title":"Probabilistic Constraint for Safety-Critical Reinforcement Learning","created":"2023-06-29","cited_by_count":11,"area":null},{"id":"2312.00342","title":"Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk","created":"2023-12-01","cited_by_count":11,"area":null},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2603.26569","title":"Machine Unlearning under Retain-Forget Entanglement","created":"2026-03-27","cited_by_count":11,"area":"safety"},{"id":"2102.13446","title":"Safe Distributional Reinforcement Learning","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2111.04894","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2309.06835","title":"Safe Reinforcement Learning with Dual Robustness","created":"2023-09-13","cited_by_count":10,"area":null},{"id":"2310.04323","title":"Adjustable Robust Reinforcement Learning for Online 3D Bin Packing","created":"2023-10-06","cited_by_count":10,"area":null},{"id":"2312.15127","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10,"area":"driving"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2506.12544","title":"Constrained Diffusers for Safe Planning and Control","created":"2025-06-14","cited_by_count":10,"area":"diffusion"},{"id":"2112.11490","title":"Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding","created":"2021-12-21","cited_by_count":9,"area":null},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"area":null}],"next_cursor":"100"}