Reinforcement Learning

Teach real, low-cost robots new tasks with AI

Train game characters with AI in Unity

Explore Google's deep learning models library

Learn to trade with reinforcement learning

Learn ML algorithms implemented in plain NumPy

Simulate robots and physics for AI training

Learn reinforcement learning (Chinese)

Learn reinforcement learning with code for the classic book

Train reinforcement learning agents reliably

Train AI in standard game and control environments

Learn RL with clean, single-file implementations

Train language models with reinforcement learning

Build a Raspberry Pi gadget that learns to capture WiFi handshakes (security research)

Train fast online learning models

Train robots in NVIDIA's realistic simulator

Train AI to play StarCraft II

Do deep learning with clear code

Study how ChatGPT-style training with human feedback works

Research AI agents in 3D game worlds

Build deep learning and RL models

Serve AI models like Kimi at scale

See AI learn to play Flappy Bird

Train reinforcement learning agents faster

Train language model agents with reinforcement learning

Train agents with reinforcement learning

Research AI for games

Do deep reinforcement learning in Keras

Build a four-legged robot pet

Train multimodal models with reinforcement learning

Learn deep reinforcement learning with Udacity

Understand LLM and RL algorithms with diagrams

Train language models with human feedback

Simulate robots in 3D

Simulate physics for reinforcement learning

See AI master the card game Dou Dizhu

Learn RL algorithms in PyTorch

Train RL agents massively in parallel

Do deep learning and RL in JavaScript

Build robot and game AI with behavior trees

Remember more with smarter Anki scheduling