Skip to content

Commit

Permalink
Fix branch name (master -> main) (#837)
Browse files Browse the repository at this point in the history 
* Fix branch name (master -> main)

* Fix branch triggers
  • Loading branch information
@jeremiahpslewis
jeremiahpslewis authored Mar 13, 2023
1 parent 41f86dc commit a481a70
Show file tree
Hide file tree
Showing 11 changed files with 30 additions and 30 deletions.
4 changes: 2 additions & 2 deletions .github/workflows/ci.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ name: CI
on:
pull_request:
branches:
- master
- main
types:
- labeled
- opened
Expand All @@ -11,7 +11,7 @@ on:
- synchronize
push:
branches:
- master
- main
tags: '*'
jobs:
test:
Expand Down
6 changes: 3 additions & 3 deletions .github/workflows/cspell.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,10 @@ name: SpellCheck
on:
push:
branches:
- master
- main
pull_request:
branches:
- master
- main

jobs:
spellchecking:
Expand All @@ -19,4 +19,4 @@ jobs:
with:
node-version: "14"
- run: npm install -g cspell
- run: cspell --config ./.cspell/cspell.json "**/*.jl" "**/*.md"
- run: cspell --config ./.cspell/cspell.json "**/*.jl" "**/*.md"
18 changes: 9 additions & 9 deletions README.md
View file
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<!-- ```@raw html -->
<div align="center">
<p>
<img src="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/raw/master/docs/src/assets/logo.svg?sanitize=true" width="320px">
<img src="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/raw/main/docs/src/assets/logo.svg?sanitize=true" width="320px">
</p>

<p>
Expand All @@ -12,7 +12,7 @@
<a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/actions?query=workflow%3ACI"><img src="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/workflows/CI/badge.svg"></a>
<a href="https://juliahub.com/ui/Packages/ReinforcementLearning/6l2TO"><img src="https://juliahub.com/docs/ReinforcementLearning/pkgeval.svg"></a>
<a href="https://juliahub.com/ui/Packages/ReinforcementLearning/6l2TO"><img src="https://juliahub.com/docs/ReinforcementLearning/version.svg"></a>
<a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/LICENSE.md"><img src="http://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat"></a>
<a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/LICENSE.md"><img src="http://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat"></a>
<a href="https://julialang.org/slack/"><img src="https://img.shields.io/badge/Chat%20on%20Slack-%23reinforcement--learnin-ff69b4"></a>
<a href="https://github.com/SciML/ColPrac"><img src="https://img.shields.io/badge/ColPrac-Contributor's%20Guide-blueviolet"></a>
</p>
Expand Down Expand Up @@ -89,7 +89,7 @@ parameters, plot results and record videos. For example:

<!-- ```@raw html -->
<img
src="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/raw/master/docs/src/assets/JuliaRL_BasicDQN_CartPole.gif?sanitize=true"
src="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/raw/main/docs/src/assets/JuliaRL_BasicDQN_CartPole.gif?sanitize=true"
width="600px">

<!--
Expand Down Expand Up @@ -119,19 +119,19 @@ subpackages. The relationship between them is depicted below:
| <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl">ReinforcementLearning.jl</a> |
| |
| +------------------------------+ |
| | <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningBase">ReinforcementLearningBase.jl</a> | |
| | <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningBase">ReinforcementLearningBase.jl</a> | |
| +----|-------------------------+ |
| | |
| | +--------------------------------------+ |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningEnvironments">ReinforcementLearningEnvironments.jl</a> | |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningEnvironments">ReinforcementLearningEnvironments.jl</a> | |
| | +--------------------------------------+ |
| | |
| | +------------------------------+ |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningCore">ReinforcementLearningCore.jl</a> | |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningCore">ReinforcementLearningCore.jl</a> | |
| +----|-------------------------+ |
| | |
| | +-----------------------------+ |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningZoo">ReinforcementLearningZoo.jl</a> | |
| +----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningZoo">ReinforcementLearningZoo.jl</a> | |
| +----|------------------------+ |
| | |
| | +-------------------------------------+ |
Expand All @@ -141,7 +141,7 @@ subpackages. The relationship between them is depicted below:
+------|----------------------------------------------------------------------------+
|
| +-------------------------------------+
+----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningExperiments">ReinforcementLearningExperiments.jl</a> |
+----&gt;+ <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningExperiments">ReinforcementLearningExperiments.jl</a> |
| +-------------------------------------+
|
| +----------------------------------------+
Expand All @@ -166,7 +166,7 @@ if you find this package useful. ❤
## ✍️ Citing

If you use `ReinforcementLearning.jl` in a scientific publication, we would
appreciate references to the [CITATION.bib](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/CITATION.bib).
appreciate references to the [CITATION.bib](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/CITATION.bib).

## ✨ Contributors

Expand Down
2 changes: 1 addition & 1 deletion docs/homepage/blog/a_practical_introduction_to_RL.jl/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15384,7 +15384,7 @@ <h2 id="Environments">Environments<a class="anchor-link" href="#Environments">&#
observe(env) # returns an observation
act!(env, a) # steps the environment forward and returns a reward
terminated(env) # returns true or false indicating whether the environment has finished</code></pre>
<p>Or if you prefer the interfaces defiend in <code>RLBase</code>, you can find a lot of examples at <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningEnvironments/src/environments/examples">RLEnvs</a>.</p>
<p>Or if you prefer the interfaces defiend in <code>RLBase</code>, you can find a lot of examples at <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningEnvironments/src/environments/examples">RLEnvs</a>.</p>

</div>
</div>
Expand Down
2 changes: 1 addition & 1 deletion ...roduction_to_reinforcement_learning_jl_design_implementations_thoughts/index.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ function Base.run(policy, env, stop_condition, hook)
end
```

Except for some corner cases, the code above is very close to [our implementation](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/src/ReinforcementLearningCore/src/core/run.jl).
Except for some corner cases, the code above is very close to [our implementation](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/src/ReinforcementLearningCore/src/core/run.jl).

### 2.2 Trajectory

Expand Down
8 changes: 4 additions & 4 deletions docs/homepage/blog/ospp_final_term_report_210370741/index.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ Establish a General Pipeline for Offline Reinforcement Learning Evaluation

In recent years, there have been several breakthroughs in the field of Reinforcement Learning with numerous practical applications where RL bots have been able to achieve superhuman performance. This is also reflected in the industry where several cutting edge solutions have been developed based on RL ([Tesla Motors](https://www.tesla.com/), [AutoML](https://cloud.google.com/automl), [DeepMind data center cooling solutions](https://deepmind.com/blog/article/deepmind-ai-reduces-google-data-centre-cooling-bill-40) just to name a few).

One of the most prominent challenges in RL is the lack of reliable environments for training RL agents. **Offline RL** has played a pivotal role in solving this problem by removing the need for the agent to interact with the environment to improve its policy over time. This brings forth the problem of not having reliable tests to verify the performance of RL algorithms. Such tests are facilitated by standard datasets ([RL Unplugged](https://arxiv.org/abs/2006.13888)\dcite{DBLP:journals/corr/abs-2006-13888}, [D4RL](https://arxiv.org/abs/2004.07219)\dcite{DBLP:journals/corr/abs-2004-07219} and [An Optimistic Perspective on Offline Reinforcement Learning](https://arxiv.org/abs/1907.04543)\dcite{agarwal2020optimistic}) that are used to train Offline RL agents and benchmark against other algorithms and implementations. [ReinforcementLearningDatasets.jl](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/master/src/ReinforcementLearningDatasets) provides a simple solution to access various standard datasets that are available for Offline RL benchmarking across a variety of tasks.
One of the most prominent challenges in RL is the lack of reliable environments for training RL agents. **Offline RL** has played a pivotal role in solving this problem by removing the need for the agent to interact with the environment to improve its policy over time. This brings forth the problem of not having reliable tests to verify the performance of RL algorithms. Such tests are facilitated by standard datasets ([RL Unplugged](https://arxiv.org/abs/2006.13888)\dcite{DBLP:journals/corr/abs-2006-13888}, [D4RL](https://arxiv.org/abs/2004.07219)\dcite{DBLP:journals/corr/abs-2004-07219} and [An Optimistic Perspective on Offline Reinforcement Learning](https://arxiv.org/abs/1907.04543)\dcite{agarwal2020optimistic}) that are used to train Offline RL agents and benchmark against other algorithms and implementations. [ReinforcementLearningDatasets.jl](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/tree/main/src/ReinforcementLearningDatasets) provides a simple solution to access various standard datasets that are available for Offline RL benchmarking across a variety of tasks.

Another problem in Offline RL is Offline Model Selection. For this, there are numerous policies that are available in [Benchmarks for Deep Off-Policy Evaluation](https://openreview.net/forum?id=kWSeGEeHvF8)\dcite{DBLP:journals/corr/abs-2103-16596}. ReinforcementLearningDatasets.jl will also help in loading policies that will aid in model selection in ReinforcementLearning.jl package.

Expand Down Expand Up @@ -561,7 +561,7 @@ RingBuffer{NamedTuple{(:reward, :episodic_reward, :discount, :state, :next_state
Support is given for D4RL policies provided in [Deep OPE](https://github.com/google-research/deep_ope)\dcite{DBLP:journals/corr/abs-2103-16596}.
#### Implementation
The policies that are given [here](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/d4rl_policies.jl) are loaded using `d4rl_policy` function.
The policies that are given [here](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/d4rl_policies.jl) are loaded using `d4rl_policy` function.
The policies are loaded into a `D4RLGaussianNetwork` which will be integrated into `GaussianNetwork` in RLCore soon.
```julia
Expand Down Expand Up @@ -590,9 +590,9 @@ function (model::D4RLGaussianNetwork)(
a, μ
end
```
The weights are loaded using the following [code](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/d4rl_policy.jl).
The weights are loaded using the following [code](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/d4rl_policy.jl).
To know the real life performance of the networks an auxiliary function `deep_ope_d4rl_evaluate` is also given which gives the unicode plot showing the performance of the policy. The code is given [here](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/master/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/evaluate.jl).
To know the real life performance of the networks an auxiliary function `deep_ope_d4rl_evaluate` is also given which gives the unicode plot showing the performance of the policy. The code is given [here](https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/main/src/ReinforcementLearningDatasets/src/deep_ope/d4rl/evaluate.jl).
#### Working
The params needed for loading the policies can be obtained using `d4rl_policy_params`
Expand Down
Loading

0 comments on commit a481a70

Please sign in to comment.