English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we model one-day international cricket games as Markovprocesses, applying forward and inverse Reinforcement Learning (RL) to developthree novel tools for the game. First, we apply Monte-Carlo learning to fit anonlinear approximation of the value function for each state of the game usinga score-based reward model. We show that, when used as a proxy for remainingscoring resources, this approach outperforms the state-of-the-artDuckworth-Lewis-Stern method used in professional matches by 3 to 10 fold.Next, we use inverse reinforcement learning, specifically a variant ofguided-cost learning, to infer a linear model of rewards based on expertperformances, assumed here to be play sequences of winning teams. From thismodel we explicitly determine the optimal policy for each state and find thisagrees with common intuitions about the game. Finally, we use the inferredreward models to construct a game simulator that models the posteriordistribution of final scores under different policies. We envisage ourprediction and simulation techniques may provide a fairer alternative forestimating final scores in interrupted games, while the inferred reward modelmay provide useful insights for the professional game to optimize playingstrategy. Further, we anticipate our method of applying RL to this game mayhave broader application to other sports with discrete states of play whereteams take turns, such as baseball and rounders.

Markov Cricket: Using Forward and Inverse Reinforcement Learning to Model, Predict And Optimize Batting Performance in One-Day International Cricket