mlsanityData to 7 Oct 2026

YRC-Bench: A Benchmark for Learning to Coordinate with Experts

arXiv 2502.09583 ↗First posted 13 Feb 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to recognize when it is likely to fail in a novel situation and to yield control to a more capable expert system. Leveraging such expert assistance can significantly improve safety and performance in such situations. Since expert assistance is costly, a central challenge is determining when to consult an expert. In this paper, we explore a novel variant of this problem, termed YRC-0, in which an agent must learn to collaborate with an expert in new environments in an unsupervised manner--that is, without interacting with the expert during training. This setting motivates the development of low-cost, robust approaches for training expert-leveraging agents. To support research in this area, we introduce YRC-Bench, an open-source benchmark that instantiates YRC-0 across diverse environments. YRC-Bench provides a standardized Gym-like API, simulated experts, an evaluation pipeline, and implementations of popular baselines. Toward tackling YRC-0, we propose a validation strategy and use a proposer-validator decomposition as a diagnostic framework to evaluate a range of learning methods, offering insights that can inform future research. Codebase: https://github.com/modanesh/YRC-Bench

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

35 of 52 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2016Concrete Problems in AI Safetycited by 1,582
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  7. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  10. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  11. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  12. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
23 more
  1. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 320
  2. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  3. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  4. 2019Vision-and-Dialog Navigationcited by 246
  5. 2020"Other-Play" for Zero-Shot Coordinationcited by 194
  6. 2021TEACh: Task-driven Embodied Agents that Chatcited by 194
  7. 2024THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulationcited by 128
  8. 2017AI Safety Gridworldscited by 108
  9. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  10. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  11. 2018Shared Autonomy via Deep Reinforcement Learningcited by 65
  12. 2022A Review of Uncertainty for Deep Reinforcement Learningcited by 36
  13. 2024HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environmentscited by 32
  14. 2014Interactive Policy Learning through Confidence-Based Autonomycited by 29
  15. 2023RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalizationcited by 27
  16. 2024Evaluating Human-AI Collaboration: A Review and Methodological Frameworkcited by 25
  17. 2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 20
  18. 2024Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learningcited by 17
  19. 2024Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detectioncited by 17
  20. 2021Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Resultscited by 14
  21. 2022Learning for Robot Decision Making under Distribution Shift: A Surveycited by 7
  22. 2021Fully General Online Imitation Learningcited by 4
  23. 2024Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptationcited by 2

Built on by

Not cited yet.