Monte Carlo RL and Blackjack

Contents Blackjack Rules Monte Carlo Basics Monte Carlo Blackjack Monte Carlo Prediction (Evaluating a fixed policy) Monte Carlo Control (Solving for an optimal policy) The OpenAI Gym Environment and Modifications...

Free Throw Bet Analysis TLDR Version

The Bet Mike McDonald bet ~$200,000 mostly at even money that he could make 90/100 free throws by the end of 2020 with unlimited attempts. He has to define when...

Assessing Generalization in Reward Learning

Contents Our Background Introduction Procgen environments What is reward learning? Initial Exploration Literature Review Deep reinforcement learning from human preferences Reward learning from human preferences and demonstrations in Atari Extrapolating...

Free Throw Bet Analysis

This post was written jointly by Max Chiswick and Mike Thompson Contents The Bet Assumptions and Simplifications Probability of making 90/100 When to reset attempts? Method 1: Binomial When to...

AI Poker Tutorial

Work in Progress! Intro This tutorial is made with two target audiences in mind: (1) Those with an interest in poker who want to understand how AI poker agents are...