Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
The precise specification of reward functions for Markov decision processes (MDPs) is often extremely difficult, motivating research into both reward elicitation and the robust solution of MDPs with imprecisely specified reward (IRMDPs). We develop new techniques for the robust optimization of IRMDPs, using the minimax regret decision criterion, that exploit the set of nondominated policies, i.e., policies that are optimal for some instantiation of the imprecise reward function. Drawing parallels to POMDP value functions, we devise a Witness-style algorithm for identifying nondominated policies. We also examine several new algorithms for computing minimax regret using the nondominated set, and examine both practically and theoretically the impact of approximating this set. Our results suggest that a small subset of the nondominated set can greatly speed up computation, yet yield very tight approximations to minimax regret.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Planning and acting in partially observable stochastic domains
Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998) · Artificial Intelligence · doi:10.1016/s0004-3702(98)00023-x · Cited by 4,149
Cited by
Conservative Agency via Attainable Utility Preservation
Turner, A. M., Hadfield-Menell, D., & Tadepalli, P. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375851 · Cited by 36
Optimal Policies Tend To Seek Power
Turner, A. M., Smith, L., Shah, R., Critch, A., & Tadepalli, P. (2019) · arXiv · doi:10.48550/arxiv.1912.01683 · Cited by 18
Towards Resolving Unidentifiability in Inverse Reinforcement Learning
Amin, K., & Singh, S. (2016) · arXiv · doi:10.48550/arxiv.1601.06569 · Cited by 13
Avoiding Side Effects in Complex Environments
Turner, A. M., Ratzlaff, N., & Tadepalli, P. (2020) · arXiv · doi:10.48550/arxiv.2006.06547 · Cited by 11
Metadata
- Authors
- Regan, K., & Boutilier, C.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2010-07-04
- Volume
- 24
- Issue
- 1
- Pages
- 1127-1133
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W1541317966
- Cited by
- 48
- References
- 1
- FWCI
- 2.86
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies. https://app.cochat.ai/papers/10.1609/aaai.v24i1.7740
- The paper
- Regan, K., & Boutilier, C. (2010). Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.1609/aaai.v24i1.7740
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.