Artificial Intelligence: Reinforcement Learning in Python

Complete guide to Reinforcement Learning, with Stock Trading and Online Advertising Applications

Artificial Intelligence: Reinforcement Learning in Python

InstructorLazy Programmer Team

Duration14h 43m

Students48.8K

Rating4.7 (10.7K)

Comidoc Analysis

Algorithmic Theory and Mathematical Foundations

Strengths

Strong Algorithmic Implementation

The curriculum provides structured paths from theoretical concepts to specific code implementations for various RL algorithms.

Best suited to

Learners with strong calculus and probability backgrounds
Students seeking to implement RL algorithms from scratch
Those interested in the mathematical theory behind decision-making agents

Less suited to

Beginners without a prerequisite understanding of optimization or dynamic programming
Learners looking for highly polished, production-ready trading bots

Editorial course preview

What the public course preview actually shows

These 3 complementary views highlight concrete, legible examples from the course presentation.

A presentation slide titled 'The Game of Go' with bullet points about AlphaGo and AlphaZero, and a diagram showing the progression from AlphaGo to AlphaZero. — Preview 1 of 3
This slide outlines the history of AI in Go, noting AlphaGo's victory over Lee Sedol and how AlphaZero achieved superhuman play without human strategy.

A presentation slide titled Video Games listing historical titles from the 70s, 90s, and recent years, accompanied by three gameplay screenshots at the bottom. — Preview 2 of 3
This slide categorizes video games by era, citing examples like Pong, Doom, and Starcraft II, alongside corresponding gameplay visuals.

A presentation slide titled 'Real-World' with bullet points comparing human infant learning to AI simulations, accompanied by an image of a simulated stick figure walking and a hex — Preview 3 of 3
This slide contrasts how human infants learn to walk from scratch versus how AIs can copy programs or use simulations to accelerate learning without physical damage.