kjabon

Posts about RL, and sundry

Intro to Vanilla Policy Gradient, continued...

Extending the Theory and intuition behind one of our introductory algorithms

19 min read · April 14, 2023

2023 · rl
Intro to Vanilla Policy Gradient

Theory and intuition behind one of our introductory algorithms

12 min read · April 14, 2023

2023 · rl
The Reinforcement Learning Problem

Before anything else, define the problem you need to solve.

15 min read · April 13, 2023

2023 · rl
Some Acme Speedbumps

Messing around with parallelization.

2 min read · March 22, 2023

2023 · rl
CoachRL Back End

Digging in to dirty details

15 min read · March 14, 2023

2023 · habits rl coachrl