ReinforcementLearning.jl

ReinforcementLearning.jl copied to clipboard

DRAFT: Add Tabular Learner

1

This pull request adds a Tabular Learner to the project. The Tabular Learner is used for reinforcement learning tasks and includes implementations for TDLearner, TabularVApproximator, and TabularQApproximator.

jeremiahpslewis

Update docs script for new 'limited' RL.jl release

1

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

jeremiahpslewis

Reactivating RLZoo

12

## Description Much of RLZoo needs to be migrated to the latest RLCore.jl / Flux.jl syntax. The goal is as follows: 1. Upgrade / refactor code in `RLZoo/src/algorithims` - Such...

jeremiahpslewis

Hey @HenriDeh, can you review the `TabularApproximator` code and let me know whether we want it in RLCore or not? I've added tests to it and modified it so it's...

jeremiahpslewis

Can't run the example code in the [Practical introduction to RL](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/docs/homepage/blog/a_practical_introduction_to_RL.jl/index.html) blog post since the source code is largely broken.

joelreymont

Update gym.jl

3

Make gym.jl compatible with current version of Gymnasium - truncation and termination info instead of done PR Checklist - [ ] Update NEWS.md? - [x] Unit tests for all structs...

SimonHashtag

See here: https://github.com/JuliaGPU/CUDA.jl/blob/master/.buildkite/pipeline.yml

jeremiahpslewis

Devmode is not working

3

I recognized lately that the compat version in the Project.toml files are not suited in order to call activate_devmode!() from `src/devmode.jl`. In my opinion it may be beneficial for developers...

Mytolo

CompatHelper: bump compat for ReinforcementLearningZoo to 0.8 for package ReinforcementLearningExperiments, (keep existing compat)

1

This pull request changes the compat entry for the `ReinforcementLearningZoo` package from `0.10.1` to `0.10.1, 0.8` for package ReinforcementLearningExperiments. This keeps the compat entries for earlier versions. Note: I have...

github-actions[bot]

PPO with MaskedPPOTrajectory

2

Hello ! I've been using PPOPolicy from your project with a MaskedPPOTrajetory. I think there are 2 issues within the update function : 1. The legal_action_mask creation line 266 :...

navaxel