The adversarial stochastic shortest path problem with unknown transition probabilities
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
We consider online learning in a special class of episodic Markovian decision processes, namely, loop-free stochastic shortest path problems. In this problem, an agent has to traverse through a finite directed acyclic graph with random transitions while maximizing the obtained rewards along the way. We assume that the reward function can change arbitrarily between consecutive episodes, and is entirely revealed to the agent at the end of each episode. Previous work was concerned with the case when the stochastic dynamics is known ahead of time, whereas the main novelty of this paper is that this assumption is lifted. We propose an algorithm called “follow the perturbed optimistic policy” that combines ideas from the “follow the perturbed leader” method for online learning of arbitrary sequences and “upper confidence reinforcement learning”, an algorithm for regret minimization in Markovian decision processes (with a fixed reward function). We prove that the expected cumulative regret of our algorithm is of order L|X||A| p T up to logarithmic factors, where L is the length of the longest path in the graph,X is the state space, A is the action space and T is the number of episodes. To our knowledge this is the first algorithm that learns and controls stochastic and adversarial components in an online fashion at the same time.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it