Playing CartPole with Deep cross-entropy method using Julia and MXNet

Hello and happy new year!

Recently I’ve been playing FrozenLake using Cross-entropy method implemented in Julia, but this time I have made my task more complicated and implemented deep cross-entropy method using MXNet in order to play CartPole.

Continue reading “Playing CartPole with Deep cross-entropy method using Julia and MXNet”

Playing CartPole with Deep cross-entropy method using Julia and MXNet

Switching from Reinforce.jl to POMDPs.jl

A week ago I have realized that Reinforce.jl package is not maintained anymore and thought about switching it to another one.

I have spent some time rewriting my code using POMDP.jl framework/ approach and moved Reinforce.jl code under deprecated.

If you browse my code you will find OpenAI text toys implementation which will be used as a base for all future developments.

Github: https://github.com/dmitrijsc/practical-rl

Switching from Reinforce.jl to POMDPs.jl

Playing Frozenlake with genetic algorithms

Our topic for today will be using Random Policy and enhance it with genetic/ evolutionary algorithms to score in different versions of FrozenLake.

About FrozenLake, OpenAI gym:
The agent controls the movement of a character in a grid world. Some tiles of the grid are walkable, and others lead to the agent falling into the water. Additionally, the movement direction of the agent is uncertain and only partially depends on the chosen direction. The agent is rewarded for finding a walkable path to a goal tile.

Let’s get started!
Continue reading “Playing Frozenlake with genetic algorithms”

Playing Frozenlake with genetic algorithms