kjabon

Posts about RL, and sundry

Imitation Learning with PWIL

An exercise on the Acrobot Swingup task

16 min read · July 18, 2023

2023 · rl
Image Regression Lessons Learned (in JAX)

An exercise in image processing

16 min read · July 10, 2023

2023 · rl
Vanilla Policy Gradient In JAX

A simple implementation using Acme

26 min read · May 3, 2023

2023 · rl
A Bit on Baselines

Reducing variance and taking names

4 min read · May 2, 2023

2023 · rl
Continuous Log Likelihood

A quick and dirty derivation

3 min read · April 24, 2023

2023 · rl