This repository contains solutions to the following environments:
- Acrobot-v1
- BipedalWalker-v3
- CartPole-v0
- LunarLander-v2
- LunarLanderContinuous-v2
- MountainCar-v0
- MountainCarContinuous-v0
- Pendulum-v0
- PongNoFrameskip-v4
More closed-form solutions can be found here.
BibTeX
Some solutions in this repo have been published in the following book (in Simplified Chinese):
@book{xiao2019,
title = {Reinforcement Learning: Theory and {Python} Implementation},
author = {Zhiqing Xiao}
year = 2019,
month = 8,
publisher = {China Machine Press},
}
All solutions will be published in the following book (in English):
@book{xiao2022,
title = {Reinforcement Learning: Theory and {Python} Implementation},
author = {Zhiqing Xiao}
publisher = {Springer Nature},
}