:book:【译】UCB CS61a SICP Python

:book: [译] UCB CS61b Java 中的数据结构

:book: [译] UCB DATA8 计算与推断思维

Structure and Interpretation of Computer Programs

:bust_in_silhouette: Multi-Armed Bandit Algorithms Library (MAB) :cop:

:book: [译] UCB DS100 数据科学的原理与技巧

:book: [译] UCB CS61a SICP Python 描述 中文版

CS 61A: Structure and Interpretation of Computer Programs, Fall 2022, UC Berkeley

A mirror website for CS61A Fall 2020 with Chinese translation.

All projects about ucb-61b(2014 spring), http://www.cs.berkeley.edu/~jrs/61b/index.html

🐭 计算机废物自学指北

This repository contains all the lab and project code solutions for the CS61C Fall 2020 course, along with detailed comments. 这个仓库包含了 CS61C Fall 2020 课程的所有 lab和项目代码解答，并附有详细注释。

UCThello - a board game demonstrator (Othello variant) with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short)

A Julia Package for providing Multi Armed Bandit Experiments

Implementations of basic concepts dealt under the Reinforcement Learning umbrella. This project is collection of assignments in CS747: Foundations of Intelligent and Learning Agents (Autumn 2017) at IIT Bombay

This repo contains all the materials and solutions of UC Berkeley CS189/289A spring semester 2024

Multi-armed bandit algorithm with tensorflow and 11 policies

Codes and templates for ML algorithms created, modified and optimized in Python and R.

🚧 UCB CS61A Solutions

All projects about ucb-cs186(fall 2013), you can get information from the course website(https://sites.google.com/site/cs186fall2013)

Author's implementation of the paper Correlated Age-of-Information Bandits.

Oware and Ouril - traditional African Mancala games with computer AI using Monte Carlo Tree Search (MCTS) with UCB (Upper Confidence Bounds) applied to trees (UCT in short)

Thompson Sampling for Bandits using UCB policy

CS70 Homework and Discussion Solutions

On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems

Assignments from UC Berkeley CS61A Fall 2024.

Foundations Of Intelligent Learning Agents (FILA) Assignments

Alquerque - a 2 player abstract strategic perfect information traditional board game with computer AI option.

🚧

We implemented a Monte Carlo Tree Search (MCTS) from scratch and we successfully applied it to Tic-Tac-Toe game.