mlsanityData to 7 Oct 2026

IPO: Interior-point Policy Optimization under Constraints

arXiv 1910.09615 ↗First posted 21 Oct 2019cs.LG math.OC stat.MLcited by 119

Not on the map. Why?

Abstract (arXiv)

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints. We propose a novel first-order policy optimization method, Interior-point Policy Optimization (IPO), which augments the objective with logarithmic barrier functions, inspired by the interior-point method. Our proposed method is easy to implement with performance guarantees and can handle general types of cumulative multiconstraint settings. We conduct extensive evaluations to compare our approach with state-of-the-art baselines. Our algorithm outperforms the baseline algorithms, in terms of reward maximization and constraint satisfaction.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 15; 2023: 32; 2024: 30; 2025: 19; 2026: 14.

119 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 76
  3. 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 60
  4. 2022Constrained Update Projection Approach to Safe Policy Optimizationcited by 55
  5. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learningcited by 51
  6. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  7. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  8. 2023Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotioncited by 33
  9. 2021Safe Driving via Expert Guided Policy Optimizationcited by 29
  10. 2023Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPscited by 27
  11. 2022Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPscited by 26
  12. 2021Safe Pontryagin Differentiable Programmingcited by 25
38 more
  1. 2023Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraintscited by 20
  2. 2021Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimizationcited by 18
  3. 2021Faster Algorithm and Sharper Analysis for Constrained Markov Decision Processcited by 18
  4. 2022Benchmarking Constraint Inference in Inverse Reinforcement Learningcited by 18
  5. 2022Evaluating Model-free Reinforcement Learning toward Safety-critical Taskscited by 18
  6. 2023SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learningcited by 16
  7. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 15
  8. 2024SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generationcited by 15
  9. 2022Robust Constrained Reinforcement Learningcited by 14
  10. 2021Safe Exploration by Solving Early Terminated MDPcited by 13
  11. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  12. 2024Off-Policy Primal-Dual Safe Reinforcement Learningcited by 13
  13. 2024Verification-Guided Shielding for Deep Reinforcement Learningcited by 13
  14. 2023Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learningcited by 12
  15. 2024Constrained Reinforcement Learning with Smoothed Log Barrier Functioncited by 12
  16. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 12
  17. 2025Probabilistic Shielding for Safe Reinforcement Learningcited by 12
  18. 2022Constrained Reinforcement Learning for Robotics via Scenario-Based Programmingcited by 11
  19. 2023Probabilistic Constraint for Safety-Critical Reinforcement Learningcited by 11
  20. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 11
  21. 2025Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimizationcited by 11
  22. 2021Safe Distributional Reinforcement Learningcited by 10
  23. 2021Safe Policy Optimization with Local Generalized Linear Function Approximationscited by 10
  24. 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraintscited by 10
  25. 2023A safe exploration approach to constrained Markov decision processescited by 10
  26. 2022Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probabilitycited by 9
  27. 2023Safe Deep Reinforcement Learning by Verifying Task-Level Propertiescited by 9
  28. 2023State-wise Constrained Policy Optimizationcited by 9
  29. 2024Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learningcited by 9
  30. 2024Embedding Safety into RL: A New Take on Trust Region Methodscited by 9
  31. 2022Towards Painless Policy Optimization for Constrained MDPscited by 8
  32. 2023Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programmingcited by 8
  33. 2024One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environmentscited by 8
  34. 2021CLARA: A Constrained Reinforcement Learning Based Resource Allocation Framework for Network Slicingcited by 7
  35. 2023Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigationcited by 7
  36. 2024Analyzing Adversarial Inputs in Deep Reinforcement Learningcited by 7
  37. 2024Constrained Reinforcement Learning Under Model Mismatchcited by 6
  38. 2025Repair-R1: Better Test Before Repaircited by 6

50 most cited of 119 All 119 (JSON)