mlsanityData to 7 Oct 2026

DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems

arXiv 2501.18086 ↗First posted 30 Jan 2025cs.LG cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent challenge. Recent research highlights the potential of leveraging pre-acquired task-agnostic knowledge to enhance both safety and sample efficiency in related tasks. Building on this insight, we propose a novel method to learn shared constraint distributions across multiple tasks. Our approach identifies the shared constraints through imitation learning and then adapts to new tasks by adjusting risk levels within these learned distributions. This adaptability addresses variations in risk sensitivity stemming from expert-specific biases, ensuring consistent adherence to general safety principles even with imperfect demonstrations. Our method can be applied to control and navigation domains, including multi-task and meta-task scenarios, accommodating constraints such as maintaining safe distances or adhering to speed limits. Experimental results validate the efficacy of our approach, demonstrating superior safety performance and success rates compared to baselines, all without requiring task-specific constraint definitions. These findings underscore the versatility and practicality of our method across a wide range of real-world tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 60 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

32 of 60 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016OpenAI Gymcited by 1,684
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2017Constrained Policy Optimizationcited by 928
  6. 2018Reward Constrained Policy Optimizationcited by 397
  7. 2018Provably Efficient Maximum Entropy Explorationcited by 240
  8. 2020Never Give Up: Learning Directed Exploration Strategiescited by 210
  9. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  10. 2019Efficient Exploration via State Marginal Matchingcited by 186
  11. 2020Reward-Free Exploration for Reinforcement Learningcited by 177
  12. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
20 more
  1. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  2. 2021URLB: Unsupervised Reinforcement Learning Benchmarkcited by 138
  3. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 109
  4. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  5. 2022CIC: Contrastive Intrinsic Control for Unsupervised Skill Discoverycited by 66
  6. 2019Worst Cases Policy Gradientscited by 52
  7. 2020Task-agnostic Exploration in Reinforcement Learningcited by 37
  8. 2019Maximum Likelihood Constraint Inference for Inverse Reinforcement Learningcited by 33
  9. 2019Learning to run a power network challenge for training topology controllerscited by 33
  10. 2020Novelty Search in Representational Space for Sample Efficient Explorationcited by 26
  11. 2021Density Constrained Reinforcement Learningcited by 25
  12. 2023Learning Safety Constraints from Demonstrations with Unknown Rewardscited by 19
  13. 2022Benchmarking Constraint Inference in Inverse Reinforcement Learningcited by 18
  14. 2021Unsupervised Reinforcement Learning in Multiple Environmentscited by 17
  15. 2023Learning Shared Safety Constraints from Multi-task Demonstrationscited by 15
  16. 2022Learning Soft Constraints From Constrained Expert Demonstrationscited by 13
  17. 2023Train Hard, Fight Easy: Robust Meta Reinforcement Learningcited by 11
  18. 2018Learning Constraints from Demonstrationscited by 9
  19. 2021Gaussian Process Constraint Learning for Scalable Chance-Constrained Motion Planning from Demonstrationscited by 6
  20. 2024Confidence Aware Inverse Constrained Reinforcement Learningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
  2. 2024Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving
  3. 2026Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
  4. 2024Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
  5. 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
  6. 2024CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
  7. 2025Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
  8. 2026Safe Meta-Reinforcement Learning via Information Space Reachability