Kyle Daruwalla
Kyle Daruwalla
Who is currently maintaining this package? I have an interest in seeing it through, and I have been helping/following JuliaReinforcementLearning/CommonRLInterface.jl. If no one is actively maintaining it, can I have...
Currently, the DiscreteSpace is defined as `{1, ..., n}` (as it should be), but the lines in `CartPole.jl` that map `{1, 2} --> {-1, 1}` are commented out. Additionally, the...
`PendulumEnv` is calculating clamped torque, but using unclamped torque in subsequent calculations. i.e. we calculate: ```julia v = clamp.(u, -env.max_torque, env.max_torque) ``` but we don't use `v` in any of...
### Motivation and description Using `trainable`, we can walk a `model` and only apply a function to trainable parameters. But the `gradient` from Zygote is a named tuple without this...
`ComposedSchedule` is only implicitly tested through the cyclic schedules. This probably leaves out edge cases.
After working a bit on #175, I feel that `replace_storage` works well for arrays of primitive types, but it doesn't work well for wrapper array types. Consider the following two...
`CuArray`s should not follow the fast path in `obsview` that returns a view of the original array, since this triggers scalar indexing for downstream operations. ref https://github.com/FluxML/Flux.jl/issues/1935
If `getobs` returns a named tuple, then `mapobs` will fail.
Ref https://github.com/JuliaML/LearnBase.jl/pull/48#issue-698461216 1. Rename LearnBase.jl ➡️ LearnAPI.jl (similar to StatsAPI.jl and DataAPI.jl) 2. Create MLBase.jl as an umbrella over MLDataPattern.jl, MLLabelUtils.jl, LossFunctions.jl, and PenaltyFunctions.jl For (2), do we want an...
In order to be usable by the neuroscience community, we would at least need to add: - [Izhikevich model](https://www.izhikevich.org/publications/spikes.pdf) - [Hodgkin-Huxley model](https://neuronaldynamics.epfl.ch/online/Ch2.S2.html)