ReinforcementLearning.jl

ReinforcementLearning.jl copied to clipboard

This is an ambitious goal that workers and learners can be relatively independent. One possible scenario may be, running fast evaluation in Julia within workers and running learner with TF/PyTorch/JAX...

findmyway

findmyway

I don't know if I did something wrong but I get the error: `Package ReinforcementLearningBase does not have DomainSets in its dependencies` when I try to precompile the project. Here's...

kir0ul

Bounds Error at UPDATE_FREQ Step

2

Hello, I've recreated a simple version of my project at the following link on my github: https://github.com/ryan-o-c/RL-Env-Debugger/blob/main/Debugger.ipynb The broad strokes are that I want to pass an image and vector...

ryan-o-c

`StopAfterEpisode` returns 1 more episode using `StepsPerEpisode()` hook

1

I was playing a bit with hooks and I found the following behavior a bit surprising: if I use the `StopAfterEpisode(10)` stopping condition, I would expect to get a result...

kir0ul

findmyway

i can save model parameters using BSON in a hook, but i don't know how can i use the model and test it on the env(without training, only testing)

alerem18

This pull request changes the compat entry for the `CommonRLSpaces` package from `0.1` to `0.1, 0.2` for package ReinforcementLearningBase. This keeps the compat entries for earlier versions. Note: I have...

github-actions[bot]

Tabular Approximator fixes (pre v0.11 changes)

1

PR Checklist - [ ] Update NEWS.md? - [ ] Unit tests for all structs / functions? - [ ] Integration and correctness tests using a simple env? - [...

jeremiahpslewis

PR Checklist - [ ] Update NEWS.md? - [ ] Unit tests for all structs / functions? - [ ] Integration and correctness tests using a simple env? - [...

jeremiahpslewis