Acerca de este Curso

21,549 vistas recientes
Certificado para compartir
Obtén un certificado al finalizar
100 % en línea
Comienza de inmediato y aprende a tu propio ritmo.
Fechas límite flexibles
Restablece las fechas límite en función de tus horarios.
Nivel avanzado
Aprox. 17 horas para completar
Inglés (English)

Habilidades que obtendrás

option pricing and risk managementsimple model for market dynamicsQ-learning using financial problemsoptimal tradingPortfolio Optimization
Certificado para compartir
Obtén un certificado al finalizar
100 % en línea
Comienza de inmediato y aprende a tu propio ritmo.
Fechas límite flexibles
Restablece las fechas límite en función de tus horarios.
Nivel avanzado
Aprox. 17 horas para completar
Inglés (English)

ofrecido por

Placeholder

New York University

Programa - Qué aprenderás en este curso

Semana
1

Semana 1

4 horas para completar

MDP and Reinforcement Learning

4 horas para completar
14 videos (Total 107 minutos), 2 lecturas, 1 cuestionario
14 videos
Prerequisites7m
Welcome to the Course5m
Introduction to Markov Decision Processes and Reinforcement Learning in Finance9m
MDP and RL: Decision Policies9m
MDP & RL: Value Function and Bellman Equation7m
MDP & RL: Value Iteration and Policy Iteration4m
MDP & RL: Action Value Function9m
Options and Option pricing7m
Black-Scholes-Merton (BSM) Model8m
BSM Model and Risk9m
Discrete Time BSM Model7m
Discrete Time BSM Hedging and Pricing8m
Discrete Time BSM BS Limit6m
2 lecturas
Jupyter Notebook FAQ10m
Hedged Monte Carlo: low variance derivative pricing with objective probabilities10m
Semana
2

Semana 2

4 horas para completar

MDP model for option pricing: Dynamic Programming Approach

4 horas para completar
7 videos (Total 59 minutos), 2 lecturas, 1 cuestionario
7 videos
Action-Value Function5m
Optimal Action From Q Function6m
Backward Recursion for Q Star8m
Basis Functions8m
Optimal Hedge With Monte-Carlo8m
Optimal Q Function With Monte-Carlo10m
2 lecturas
Jupyter Notebook FAQ10m
QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds10m
Semana
3

Semana 3

4 horas para completar

MDP model for option pricing - Reinforcement Learning approach

4 horas para completar
8 videos (Total 71 minutos), 3 lecturas, 1 cuestionario
8 videos
Batch Reinforcement Learning9m
Stochastic Approximations8m
Q-Learning8m
Fitted Q-Iteration10m
Fitted Q-Iteration: the Ψ-basis9m
Fitted Q-Iteration at Work11m
RL Solution: Discussion and Examples11m
3 lecturas
Jupyter Notebook FAQ10m
QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds and The QLBS Learner Goes NuQLear10m
Course Project Reading: Global Portfolio Optimization10m
Semana
4

Semana 4

5 horas para completar

RL and INVERSE RL for Portfolio Stock Trading

5 horas para completar
10 videos (Total 82 minutos), 2 lecturas, 1 cuestionario
10 videos
Introduction to RL for Trading12m
Portfolio Model8m
One Period Rewards6m
Forward and Inverse Optimisation10m
Reinforcement Learning for Portfolios9m
Entropy Regularized RL8m
RL Equations10m
RL and Inverse Reinforcement Learning Solutions10m
Course Summary3m
2 lecturas
Jupyter Notebook FAQ10m
Multi-period trading via Convex Optimization10m

Reseñas

Principales reseñas sobre REINFORCEMENT LEARNING IN FINANCE

Ver todas las reseñas

Acerca de Programa especializado: Machine Learning and Reinforcement Learning in Finance

Machine Learning and Reinforcement Learning in Finance

Preguntas Frecuentes

¿Tienes más preguntas? Visita el Centro de Ayuda al Alumno.