Indexability and Rollout Policy for Multi-State Partially Observable\n Restless Bandits
Bibliographic record
Abstract
Restless multi-armed bandits with partially observable states has\napplications in communication systems, age of information and recommendation\nsystems. In this paper, we study multi-state partially observable restless\nbandit models. We consider three different models based on information\nobservable to decision maker -- 1) no information is observable from actions of\na bandit 2) perfect information from bandit is observable only for one action\non bandit, there is a fixed restart state, i.e., transition occurs from all\nother states to that state 3) perfect state information is available to\ndecision maker for both actions on a bandit and there are two restart state for\ntwo actions. We develop the structural properties. We also show a threshold\ntype policy and indexability for model 2 and 3. We present Monte Carlo (MC)\nrollout policy. We use it for whittle index computation in case of model 2. We\nobtain the concentration bound on value function in terms of horizon length and\nnumber of trajectories for MC rollout policy. We derive explicit index formula\nfor model 3. We finally describe Monte Carlo rollout policy for model 1 when it\nis difficult to show indexability. We demonstrate the numerical examples using\nmyopic policy, Monte Carlo rollout policy and Whittle index policy. We observe\nthat Monte Carlo rollout policy is good competitive policy to myopic.\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 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| 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".