diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..aa8b6af --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,8 @@ +# Default ignored files +/shelf/ +/workspace.xml +# Datasource local storage ignored files +/../../../../../../../:\UNI\2020\DeepNeuron\GitWorkshop\GitWorkshop\.idea/dataSources/ +/dataSources.local.xml +# Editor-based HTTP Client requests +/httpRequests/ diff --git a/.idea/GitWorkshop.iml b/.idea/GitWorkshop.iml new file mode 100644 index 0000000..c821916 --- /dev/null +++ b/.idea/GitWorkshop.iml @@ -0,0 +1,11 @@ + + + + + + + + + + \ No newline at end of file diff --git a/.idea/inspectionProfiles/Project_Default.xml b/.idea/inspectionProfiles/Project_Default.xml new file mode 100644 index 0000000..03d9549 --- /dev/null +++ b/.idea/inspectionProfiles/Project_Default.xml @@ -0,0 +1,6 @@ + + + + \ No newline at end of file diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml new file mode 100644 index 0000000..105ce2d --- /dev/null +++ b/.idea/inspectionProfiles/profiles_settings.xml @@ -0,0 +1,6 @@ + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..a891b7d --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..82ae704 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..94a25f7 --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file diff --git a/README.md b/README.md index dda25a4..25b371d 100644 --- a/README.md +++ b/README.md @@ -1,30 +1,13 @@ -# Git Workshop Exercise -In this exercise your team will create a mini-website (with simple markdown pages) documenting your project. -There are several tasks to complete (listed as `GitLab Issues`), but take these with a pinch of salt. -The questions should get you thinking about positive open-source documentation, but the priority here is to **practice conflict resolution with Git**. -To complete the exercises you'll just need to edit markdown files (end with a `.md`) with any text-editor. -The `#`'s are for headings (more `#` means smaller). -Wrap text in `*` for italics or `**` for bold and `\`` for code-blocks (`\`\`\`` for multi-line code blocks). -Think very carefully about your actions (creating files, editing files, where you create a branch from...) and discuss any doubts/questions with your teammates. -If you stay conscious of what you're doing, you'll quickly become a Git lean mean machine! -Please **work on merging and fixing conflicts together** where possible. -Note that it may be useful to use a visual UI to show what changes have been made (VScode is a great choice). +#Who are we +We are the dynamic balancing team from DeepNeuron. We are a reinforcement learning focused group working towards the end goal of +having an AI dynamically balanced to always provide a reasonable challenge to the player. Going forward this could be implemented by +game developers to help keep players engaged in the growing games market with a perfect challenge provided. -# Setup and Workflow -Sart by forking and cloning this repository (`git clone YOUR_REPO_LINK`). -There will be a fork button near the top right hand side of the screen (left of the blue clone button). -**Only one person per-team should do this** (you can share screen with everyone else so they know how too though)! -Once you've got your own GitLab repository clone it (hitting the clone button and then HTTPS will give you the URL) to use in `git clone REPO_LINK`. -Once everyone knows what task they'll start with create a feature branch to work in (`git checkout -b some-feature-branch`, but use a meaningful name which doesn't include the words feature branch). -Although it won't be immidiately useful, do recall that you by default branch from your current (**not `master`**) branch. - -> Remember, each task should be completed in a new branch! - -You should gradually commit (`git commit -m "ADDED COOL THING/CHANGED BLAH BLAH BLAH"`) your changes. -Once you've completed a task make sure to push (`git push`) everything and create a pull request (through the website). - -Before creating a pull request remember to get the latest changes (`git pull`). -This is one place where conflicts may occur (hint - this is when rebases are useful). +#Moar details. +This semester we are working our way up through reinforcement learning algorithms with Gym enviroments. We have implented a DQN to solve cartpole +before moving on to ATARI games and building up to a DDQN algorithm. When moving to ATARI we increased our networks by introducing CNN layers to +extract features out of the screen. Moving forward we intend on developing actor critic and then PPO networks. Once these algorithms have been explored +and our agent can kick ass we will return to the goal of dynamic balancing.