ReinforcementLearning.jl

ReinforcementLearning.jl copied to clipboard

Should be fairly easy to do with the new optimizer of Flux and @parallel and [remote channels](https://docs.julialang.org/en/latest/manual/parallel-computing/#Channels-and-RemoteChannels-1).

jbrea

I've spent some time working on reimplementing https://github.com/liuanji/WU-UCT . It seems to work well. I'll add some experiments after https://github.com/JuliaReinforcementLearning/ReinforcementLearningZoo.jl/pull/14 gets merged.

findmyway

https://arxiv.org/abs/1810.09026

findmyway

add CUDA accelerated Env

5

Nvidia has ported Atari to CUDA: https://github.com/NVlabs/cule The biggest benefit is, the data are in GPU memory, thus avoided memory copy between host & device. My ideas are: # add...

norci

Waiting for @xiaodaigh to register it https://github.com/xiaodaigh/Game2048.jl 😉

findmyway

Do we want a wrapper of [bsuite](https://github.com/deepmind/bsuite)?

jbrea

https://github.com/geek-ai/MAgent I just did a quick test. It seems easy to support. Ping me if anyone really needs this environment.

findmyway

Would be nice to wrap [Box2D](https://github.com/erincatto/Box2D) and include some environments like the ones of [OpenAI Gym](https://github.com/openai/gym/tree/master/gym/envs/box2d).

findmyway

bullet3 environment

3

https://github.com/bulletphysics/bullet3 See also [here](https://discourse.julialang.org/t/julia-interface-to-bullet-physics/12617)

findmyway

https://github.com/JuliaReinforcementLearning/ViZDoom.jl/issues/7

findmyway