Harrison Delecki

Results 2 issues of Harrison Delecki

Hello, The ADVI tutorial example fails with Zygote AD. Running the following example ```julia using Random using Turing, Zygote using Turing: Variational Turing.setadbackend(:zygote) x = randn(2000) @model function model(x) s...

Running the `halfcheetah_ars.jl` example, I expected to see policy behavior similar to what is shown in the [docs](https://dojo-sim.github.io/Dojo.jl/dev/reinforcement_learning.html). Instead, I see that ARS gets a mean reward of around -23...