MétaCan
Menu
Back to cohort
Record W2734441105

Acceleration of Iterative Methods for Markov Decision Processes

2010· dissertation· en· W2734441105 on OpenAlexfundno aff
Oleksandr Shlakhter

Bibliographic record

VenueTSpace (University of Toronto) · 2010
Typedissertation
Languageen
FieldDecision Sciences
TopicSimulation Techniques and Applications
Canadian institutionsnot available
FundersUniversity of Toronto
KeywordsAccelerationComputer scienceMarkov decision processMarkov processMathematicsStatisticsPhysicsClassical mechanics
DOInot available

Abstract

fetched live from OpenAlex

This research focuses on Markov Decision Processes (MDP). MDP is one of the most important and challenging areas of Operations Research. Every day people make many decisions: today's decisions impact
\ntomorrow's and tomorrow's will impact the ones made the day after. Problems in Engineering, Science, and Business often pose similar challenges: a large number of options and uncertainty about the
\nfuture. MDP is one of the most powerful tools for solving such problems.
\n
\nThere are several standard methods for finding optimal or approximately optimal policies for MDP. Approaches widely employed
\nto solve MDP problems include value iteration and policy iteration. Although simple to implement, these approaches are, nevertheless, limited in the size of problems that can be solved, due to excessive
\ncomputation required to find close-to-optimal solutions.
\n
\nMy thesis proposes a new value iteration and modified policy iteration methods for classes of the expected discounted MDPs and
\naverage cost MDPs.
\n
\nWe establish a class of operators that can be integrated into value iteration and modified policy iteration algorithms for Markov Decision Processes, so as to speed up the convergence of the iterative search. Application of these operators requires a little additional computation per iteration but reduces the number of iterations significantly. The development of the acceleration operators relies on two key properties of Markov operator, namely
\ncontraction mapping and monotonicity in a restricted region. Since Markov operators of the classical value iteration and modified
\npolicy iteration methods for average cost MDPs do not possess the contraction mapping property, for these models we restrict our study to average cost problems that can be formulated as the stochastic shortest path problem.
\n
\nThe performance improvement is significant, while the implementation of the operator into the value iteration is trivial. Numerical studies show that the accelerated methods can be hundreds of times more efficient for solving MDP problems than the other known approaches. The computational savings can be significant especially
\nwhen the discount factor approaches 1 and the transition probability matrix becomes dense, in which case the standard iterative algorithms suffer from slow convergence.

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 distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.973
Threshold uncertainty score0.992

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0080.000

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.

Opus teacher head0.078
GPT teacher head0.461
Teacher spread0.382 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designOther design
Domainnot available
GenreMethods

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".

Quick stats

Citations2
Published2010
Admission routes1
Has abstractyes

Explore more

Same venueTSpace (University of Toronto)Same topicSimulation Techniques and ApplicationsFrench-language works237,207