Name: Statistical Reinforcement Learning
ISBN: 9781439856895

Book information

Authors: Tetsuro Morimura verified identity
First published: 2012
Editions known: 1
Publishers: CRC Press
ISBN-13: 9781439856895
Main topics: Reinforcement Learning for Finance
Also covers: Financial Machine Learning
Related site topics: Machine Learning for Market Forecasting, Reinforcement Learning for Trading

Overview

Statistical Reinforcement Learning is a book by Tetsuro Morimura, first published in 2012. In this catalogue it is classified mainly under Reinforcement Learning for Finance, with secondary coverage of Financial Machine Learning.

Audience and depth. The rule-based model places its mathematical difficulty at advanced level (7/10); readers are typically expected to know calculus, linear algebra, machine learning, optimization, probability theory and statistics.

Orientation. The theory-versus-practice balance could not be determined from metadata. The archive holds 6 papers whose topics and vocabulary overlap with this book; those links are inferred (see the research connections below).

How to read this page. Topics, difficulty, prerequisites and orientation are model-derived (rule-based, rule_based_v1) from bibliographic metadata such as title, subject headings and edition data. They were not produced by reading the book and are not a review. Relevance confidence is 82% and difficulty confidence is 78%; the catalogue lists no ratings or awards.

Research assessment

Rule-based and model-derived from metadata (title, subject headings, edition data). These are not reviews or ratings; see the evidence below.

Quant-finance relevance	39/100 confidence 82% Score 39.5/100. Strongest: technical_depth 0.62, quant_relevance 0.30; weakest: practical_applicability 0.00. Evidence: topic_hints:'finance'.
Mathematical difficulty	Advanced (7/10) confidence 78%
Prerequisites	calculus, linear algebra, machine learning, optimization, probability theory, statistics
Metadata quality	91%

Difficulty evidence (4 signals)

dynamic_programming_rl matched in subjects: “reinforcement learning”
dynamic_programming_rl matched in title: “reinforcement learning”
machine_learning matched in subjects: “machine learning”
statistical_inference matched in subjects: “statistical methods”

Research connections

Related papers on this site

Similarity of research area (shared vocabulary, topics and methods). Not citations: the paper does not necessarily cite this book.

Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization Topic similarity inferred similarity 0.61
Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information Topic similarity inferred similarity 0.60
The Role of Deep Learning in Financial Asset Management: A Systematic Review Topic similarity inferred similarity 0.58
An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Trading Topic similarity inferred similarity 0.52
Model Based Reinforcement Learning with Non-Gaussian Environment Dynamics and its Application to Portfolio Optimization Topic similarity inferred similarity 0.52
CAD: Clustering And Deep Reinforcement Learning Based Multi-Period Portfolio Management Strategy Topic similarity inferred similarity 0.51

Methods covered

Machine Learning (Non-Deep) inferred
Reinforcement Learning inferred

Similar books

Foundations of Reinforcement Learning with Applications in Finance inferred similarity 0.55
Reinforcement Learning for Finance inferred similarity 0.54
Markov Decision Processes with Applications to Finance inferred similarity 0.50
Machine Learning for Asset Management inferred similarity 0.46
Machine Learning for Financial Engineering inferred similarity 0.41

Author profiles

Tetsuro Morimura verified identity

External resources

Open Library
Search on Amazon (ISBN-13 9781439856895) (search link; may be an affiliate link)

Relationship graph

Solid lines are verified facts (authorship from persistent identifiers, editions); dashed lines are inferred by rules or similarity. Open in the full explorer.

Interactive relationship graph (requires JavaScript). The relationships are also listed as text below it once loaded.