\( \newcommand{\vect}[1]{\mathbf{#1}} \newcommand{\mat}[1]{\mathbf{#1}} \newcommand{\R}{\mathbb{R}} \newcommand{\E}{\mathbb{E}} \newcommand{\Prob}{\mathbb{P}} \newcommand{\T}{^{\top}} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\abs}[1]{\lvert #1 \rvert} \newcommand{\ihat}{\mkern1mu\hat{\boldsymbol{\imath}}\mkern2mu} \newcommand{\jhat}{\mkern1mu\hat{\boldsymbol{\jmath}}\mkern2mu} \newcommand{\pd}[2]{\frac{\partial #1}{\partial #2}} \newcommand{\argmax}{\operatorname*{arg\,max}} \newcommand{\argmin}{\operatorname*{arg\,min}} \newcommand{\cdata}[1]{\class{c-data}{#1}} \newcommand{\cmodel}[1]{\class{c-model}{#1}} \newcommand{\ctruth}[1]{\class{c-truth}{#1}} \newcommand{\cgrad}[1]{\class{c-grad}{#1}} \newcommand{\closs}[1]{\class{c-loss}{#1}} \newcommand{\cparam}[1]{\class{c-param}{#1}} \newcommand{\csecond}[1]{\class{c-second}{#1}} \renewcommand{\,}{\mkern3mu} \)

RL06 · Advanced RL

A free, illustrated L4 course of 11 modules in the Reinforcement Learning track. Modules include: Exploration in deep RL; Offline RL; Imitation learning.

RL06 L4 · Expert 11 modules · about 44 lessons Planned · Ring 4

Part of the Reinforcement Learning track. Ships in Ring 4 (Expert) of the roadmap.

Modules

1. Exploration in deep RL
2. Offline RL
3. Imitation learning
4. Inverse RL and reward learning
5. Hierarchical RL
6. Multi-agent RL
7. Meta-RL and multi-task RL
8. Safe and constrained RL
9. Control as inference
10. RL theory basics
11. RL as sequence modeling

Signature illustrations

The pictures a learner should still see in their head a year later:

Distribution shift in offline data, the dataset-aggregation loop, payoff matrices with learning dynamics, a hierarchy of options.

Status

This course is planned, not written yet. It ships with Ring 4 (Expert).

Every lesson will follow the same twelve-part blueprint with at least three purpose-made figures. Watch the repository to hear when modules ship, or help write and review it.