Catalog
Course

Deep Reinforcement Learning

From RL Foundations to PPO, SAC, and the Spinning Up Toolkit

Intermediate 9h estimated 4 modules
Reinforcement LearningPolicy GradientsDeep LearningPyTorchTensorFlow
Modules Syllabus
1
RL Foundations
Agents, environments, policies, value functions, and the mathematical landscape of modern RL algorithms.
2
Policy Gradient Algorithms
VPG, TRPO, and PPO — the on-policy family of algorithms that directly optimize the policy objective.
3
Off-Policy Methods & Tooling
DDPG, TD3, and SAC for continuous control, plus the Spinning Up toolkit for running, logging, and benchmarking experiments.
4
Visual Reinforcement Learning
Train agents directly from pixels using convolutional policies, frame stacking, and ViZDoom — from a stationary-enemy basic scenario to multi-target arena combat.