mlsanityData to 7 Oct 2026

Safe Reinforcement Learning via Curriculum Induction

arXiv 2006.12136 ↗First posted 22 Jun 2020cs.LG cs.AI cs.ROcited by 73

Not on the map. Why?

Abstract (arXiv)

In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations during exploration with high probability, but both the probabilistic guarantees and the smoothness assumptions inherent in the priors are not viable in many scenarios of interest such as autonomous driving. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor that saves the agent from violating constraints during learning. In this model, we introduce the monitor that neither needs to know how to do well at the task the agent is learning nor needs to know how the environment works. Instead, it has a library of reset controllers that it activates when the agent starts behaving dangerously, preventing it from doing damage. Crucially, the choices of which reset controller to apply in which situation affect the speed of agent learning. Based on observing agents' progress, the teacher itself learns a policy for choosing the reset controllers, a curriculum, to optimize the agent's final policy reward. Our experiments use this framework in two environments to induce curricula for safe and efficient learning.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 17; 2023: 15; 2024: 11; 2025: 7; 2026: 5.

73 papers.

Sort:

By area:

  1. 2021Curriculum Learning: A Surveycited by 257
  2. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  3. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  4. 2022Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentationcited by 63
  5. 2022Constrained Policy Optimization via Bayesian World Modelscited by 55
  6. 2021Safe Reinforcement Learning Using Advantage-Based Interventioncited by 45
  7. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  8. 2021Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violationscited by 36
  9. 2021Safe Reinforcement Learning with Linear Function Approximationcited by 33
  10. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  11. 2021Direct Behavior Specification via Constrained Reinforcement Learningcited by 30
  12. 2022Towards Safe Reinforcement Learning with a Safety Editor Policycited by 28
38 more
  1. 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithmscited by 27
  2. 2021Self-Paced Context Evaluation for Contextual Reinforcement Learningcited by 25
  3. 2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 20
  4. 2023Proximal Curriculum for Reinforcement Learning Agentscited by 19
  5. 2023Identifiability and Generalizability in Constrained Inverse Reinforcement Learningcited by 16
  6. 2023Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstrationcited by 14
  7. 2021Risk-Aware Transfer in Reinforcement Learning using Successor Featurescited by 12
  8. 2022Near-Optimal Multi-Agent Learning for Safe Coverage Controlcited by 11
  9. 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraintscited by 10
  10. 2021Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shieldingcited by 9
  11. 2022Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RLcited by 9
  12. 2022Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probabilitycited by 9
  13. 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 9
  14. 2024Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networkscited by 8
  15. 2021Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planningcited by 7
  16. 2021Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial timecited by 6
  17. 2022SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisitioncited by 6
  18. 2024Proximal Curriculum with Task Correlations for Deep Reinforcement Learningcited by 6
  19. 2024Safe Reinforcement Learning in Black-Box Environments via Adaptive Shieldingcited by 6
  20. 2021Automatic Risk Adaptation in Distributional Reinforcement Learningcited by 5
  21. 2022Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agentscited by 5
  22. 2022Effects of Safety State Augmentation on Safe Explorationcited by 5
  23. 2023Reinforcement Learning by Guided Safe Explorationcited by 5
  24. 2021Automatic Curricula via Expert Demonstrationscited by 4
  25. 2021DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Interventioncited by 4
  26. 2023Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraintscited by 4
  27. 2024Enhancing Reinforcement Learning Agents with Local Guidescited by 4
  28. 2025A Survey of Reinforcement Learning for Optimization in Automationcited by 4
  29. 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agentscited by 4
  30. 2021Learning to Be Cautiouscited by 3
  31. 2021Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehiclescited by 3
  32. 2023On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approachcited by 3
  33. 2024A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safetycited by 3
  34. 2021Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approachcited by 2
  35. 2023ConBaT: Control Barrier Transformer for Safe Policy Learningcited by 2
  36. 2024Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  37. 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  38. 2025Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMscited by 2

50 most cited of 73 All 73 (JSON)