Q Learning From Scratch – Using Q Tables
Back to basics - Q learning with a Q Table. Built in Python with the Frozen Lake OpenAI gym environment.
Join me on discord at - https://discord.gg/dnhsk3pD2V.
See the full project, with a test run block at https://github.com/bobcowher/frozen-lake-q-table
Видео Q Learning From Scratch – Using Q Tables канала Robert Cowher - DevOps, Python, AI
Join me on discord at - https://discord.gg/dnhsk3pD2V.
See the full project, with a test run block at https://github.com/bobcowher/frozen-lake-q-table
Видео Q Learning From Scratch – Using Q Tables канала Robert Cowher - DevOps, Python, AI
Комментарии отсутствуют
Информация о видео
10 мая 2025 г. 20:26:09
00:34:35
Другие видео канала
Zombies & AI - Part 7 - Adding Sounds
Solving Mazes with Reinforcement Learning - Part 1 - A Quick Intro
Solving Mazes with Reinforcement Learning - Part 11 - Results & Next Steps
Building a Web App with RAG & ChatGPT - Part 4 - Querying the Model
Solving Mazes with Reinforcement Learning - Part 9 - Building the Test Method
Playing Breakout with Deep Reinforcement Learning - Part 2
DualShock Lunar Lander - Using a PlayStation controller w/OpenAI Gym
Zombies & AI - Part 8 - Converting to OpenAI Gym
Zombies & AI - Part 4 - Bullets!
Robotic Arm Manipulation with Human Experiences & HRL - Part 2 - Setting up the Environment
Building a Web App with RAG & ChatGPT - Part 3 - Building the File Processor
Robotic Arm Manipulation with Reinforcement Learning - Part 3 - Building the Replay Buffer
Zombies and AI - Part 10 - Building the ReplayBuffer class
Robotic Arm Manipulation with Reinforcement Learning - Part 6 - Testing & Experimentation
Solving Mazes with Reinforcement Learning - Part 3 - Building the Critic Model
Robotic Arm Manipulation with Reinforcement Learning - Part 2 - Building the Networks
Reinforcement Learning on AMD GPUs? Trying out the Radeon 7900 XTX(so you don't have to)
Zombies & AI - Part 5 - Hunting Zombies
Robotic Arm Manipulation with Human Experiences & HRL - Part 4 - Collecting Human Experiences
Solving Mazes with Reinforcement Learning - Part 5 - Building the Buffer Class
