search

CarloLucibello / DeepRLexamples.jl

Deep Reinforcement Learning examples using Julia
Other
20 stars 5 forks source link

saying hi #1

Open CarloLucibello opened 6 years ago

CarloLucibello commented 6 years ago

Hi @etotheipluspi @evizero @denizyuret @ilkerkesen @ozanarkancan @sglyon, I've been writing some deep reinforcement examples using julia and knet and I'm pinging you just to let you know, since i think you might be interested and also since I used some of your code (especially @ilkerkesen's).

Reinforcement learning situation in julia is kind of fragmented, and what could have been the reference package, https://github.com/JuliaML/Reinforce.jl, seems unfinished and unmaintened.

I though It would be nice to have a julia repo with neat examples and as little as possible external dependencies. This repo could be moved to the JuliaML org at a certain point.

Bye, Carlo

some related julia repos: https://github.com/ilkerkesen/rl https://github.com/JuliaML/Reinforce.jl https://github.com/ozanarkancan/ReinforcementLearning.jl https://github.com/sisl/DeepRL.jl https://github.com/JuliaPOMDP/POMDPs.jl https://github.com/Evizero/ReinforcementLearning.jl https://github.com/JuliaPOMDP/POMDPReinforce.jl

and discussions: https://github.com/JuliaML/Reinforce.jl/issues/10 https://github.com/JuliaML/Reinforce.jl/issues/5 https://github.com/JuliaML/Reinforce.jl/issues/2 https://github.com/JuliaPOMDP/POMDPs.jl/issues/142 https://github.com/Evizero/ReinforcementLearning.jl/blob/master/docs/src/devdocs/design.md

Evizero commented 6 years ago

Sure. I'd say the whole RL side of things is pretty much up for grabs.

Evizero commented 6 years ago

Since we are having this conversation, I experimented a little with trying to build on POMDPs in my attempt to design an RL package. i have a writeup of my thoughts and findings here https://github.com/Evizero/ReinforcementLearning.jl/blob/master/docs/src/devdocs/design.md

jbrea commented 6 years ago

Hi @CarloLucibello @etotheipluspi @Evizero @denizyuret @ilkerkesen @ozanarkancan @sglyon @tejank10

I am sorry to further add to the fragmentation, but here is the result of my continued work on a reinforcement learning package that initially focused on tabular environments. Maybe we can at some point merge all approaches in one package?

MathisFederico commented 4 years ago

I'm very curious to know the whereabouts of reinforcement learning in Julia in 2020 !