Optimal Policies for Convex Symmetric Stochastic Dynamic Teams and their\n Mean-field Limit
Bibliographic record
Abstract
This paper studies convex stochastic dynamic team problems with finite and\ninfinite time horizons under decentralized information structures. First, we\nintroduce two notions called exchangeable teams and symmetric information\nstructures. We show that in convex exchangeable team problems an optimal policy\nexhibits a symmetry structure. We give a characterization for such\nsymmetrically optimal teams for a general class of convex dynamic team problems\nunder a mild conditional independence condition. In addition, through\nconcentration of measure arguments, we establish the convergence of optimal\npolicies for teams with $N$ decision makers to the corresponding optimal\npolicies for symmetric mean-field teams with infinitely many decision makers.\nAs a by-product, we present an existence result for convex mean-field teams,\nwhere the main contribution of our paper is with respect to the information\nstructure in the system when compared with the related results in the\nliterature that have either assumed a classical information structure or a\nstatic information structure. We also apply these results to the important\nspecial case of Linear Quadratic Gaussian (LQG) team problems, where while for\npartially nested LQG team problems with finite time horizons it is known that\nthe optimal policies are linear, for infinite horizon problems the linearity of\noptimal policies has not been established in full generality. We also study\naverage cost finite and infinite horizon dynamic team problems with a symmetric\npartially nested information structure and obtain globally optimal solutions\nwhere we establish linearity of optimal policies.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".