Spatial Grounding before Trusting Aligned Offline Values

Authors

  • Adrian Hall Author
  • Jack Warren Author
  • Liam Cooper Author

Abstract

Cross-domain value alignment can resolve numerical incompatibility while leaving spatial state representations inadequate. Evaluation should preserve relevant perceptual relations and behavior support, then check policy outcomes independently. A correct-sounding explanation does not establish that the transferred values are grounded in the target scene or that the chosen action has the predicted consequence. This focused synthesis develops an empirical comparison that preserves the terminal action, observation process, and total verification cost. Its proposed tests are prospective; no new simulation run, model-training result, or intervention effect is reported.

References

  1. Z. Qiao, J. Lyu, C. Bai, P. Wang, S. Gao, and S. Qiu, “Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets,” Proceedings of the 2026 International Conference on Machine Learning, 2026.
  2. S. Chen, T. Zhu, R. Zhou, J. Zhang, S. Gao, J. Niebles, M. Geva, J. He, J. Wu, and M. Li, “Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas,” Proceedings of the 42nd International Conference on Machine Learning, 2025.
  3. Sang, Yinghao. “Towards Explainable RAG: Interpreting the Influence of Retrieved Passages on Generation.” 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC), IEEE, 2025, pp. 397-400. https://doi.org/10.1109/raiic65850.2025.11170170.
  4. Kumar, Aviral, Aurick Zhou, George Tucker, and Sergey Levine. “Conservative Q-Learning for Offline Reinforcement Learning.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1179–1191. https://arxiv.org/abs/2006.04779.
  5. Lewis, Patrick, et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. https://arxiv.org/abs/2005.11401.
  6. Geifman, Yonatan, and Ran El-Yaniv. “Selective Classification for Deep Neural Networks.” Advances in Neural Information Processing Systems, vol. 30, 2017. https://arxiv.org/abs/1705.08500.
  7. Ovadia, Yaniv, et al. “Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift.” Advances in Neural Information Processing Systems, vol. 32, 2019. https://arxiv.org/abs/1906.02530.
  8. Bertsimas, Dimitris, and Melvyn Sim. “The Price of Robustness.” Operations Research, vol. 52, no. 1, 2004, pp. 35–53. https://doi.org/10.1287/opre.1030.0065.
  9. Rasmussen, Carl Edward, and Christopher K. I. Williams. Gaussian Processes for Machine Learning. MIT Press, 2006. https://gaussianprocess.org/gpml/.
  10. Hu, Edward J., et al. “LoRA: Low-Rank Adaptation of Large Language Models.” International Conference on Learning Representations, 2022. https://openreview.net/forum?id=nZeVKeeFYf9.
  11. Guo, Chuan, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. “On Calibration of Modern Neural Networks.” Proceedings of the 34th International Conference on Machine Learning, PMLR, vol. 70, 2017, pp. 1321–1330. https://proceedings.mlr.press/v70/guo17a.html.

Downloads

Published

2026-06-13

Versions

Issue

Vol. 2 No. 6 (2026): June 2026

Section

Articles