Reactivate docs (#842)

* Reactivate docs

* Fix config.json

* basic fixes

* Spaces in paths

* Try path fix

* Temporarily drop most experiments

* Tweak config.json

* Drop problematic dependencies

* Try to get stuff to run?

* Tweak imports

.github/workflows/ci.yml

@@ -144,52 +144,52 @@ jobs:
             Pkg.build("ReinforcementLearningExperiments")
             Pkg.test("ReinforcementLearningExperiments")'
 
-  # docs:
-  #   name: Documentation
-  #   runs-on: ubuntu-latest
-  #   steps:
-  #     - uses: actions/checkout@v2
-  #     - name: Setup python
-  #       uses: actions/setup-python@v1
-  #       with:
-  #         python-version: ${{ matrix.python-version }}
-  #         architecture: ${{ matrix.arch }}
-  #     - run: python -m pip install --user matplotlib
-  #     - uses: julia-actions/setup-julia@v1
-  #       with:
-  #         version: '1.8'
-  #     - name: Build homepage
-  #       run: |
-  #         cd docs/homepage
-  #         julia --project --color=yes -e '
-  #           using Pkg; Pkg.instantiate();
-  #           using NodeJS; run(`$(npm_cmd()) install highlight.js`);
-  #           using Franklin;
-  #           optimize()' > build.log
-
-  #     - name: Make sure homepage is generated without error
-  #       run: |
-  #         if grep -1 "Franklin Warning" build.log; then
-  #           echo "Franklin reported a warning"
-  #           exit 1
-  #         else
-  #           echo "Franklin did not report a warning"
-  #         fi
-
-  #     - name: Build docs
-  #       run: |
-  #         cd docs
-  #         julia --project --color=yes -e '
-  #           using Pkg; Pkg.instantiate();
-  #           include("make.jl")'
-  #         mv build homepage/__site/docs
-
-  #     - name: Deploy to the main repo
-  #       uses: peaceiris/actions-gh-pages@v3
-  #       if: ${{ github.event_name == 'push' }}
-  #       with:
-  #         deploy_key: ${{ secrets.ACTIONS_DEPLOY_KEY }}
-  #         external_repository: JuliaReinforcementLearning/JuliaReinforcementLearning.github.io
-  #         force_orphan: true
-  #         publish_branch: master
-  #         publish_dir: ./docs/homepage/__site
+  docs:
+    name: Documentation
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: ${{ matrix.arch }}
+      - run: python -m pip install --user matplotlib
+      - uses: julia-actions/setup-julia@v1
+        with:
+          version: '1.8'
+      - name: Build homepage
+        run: |
+          cd docs/homepage
+          julia --project --color=yes -e '
+            using Pkg; Pkg.instantiate();
+            using NodeJS; run(`$(npm_cmd()) install highlight.js`);
+            using Franklin;
+            optimize()' > build.log
+
+      - name: Make sure homepage is generated without error
+        run: |
+          if grep -1 "Franklin Warning" build.log; then
+            echo "Franklin reported a warning"
+            exit 1
+          else
+            echo "Franklin did not report a warning"
+          fi
+
+      - name: Build docs
+        run: |
+          cd docs
+          julia --project --color=yes -e '
+            using Pkg; Pkg.instantiate();
+            include("make.jl")'
+          mv build homepage/__site/docs
+
+      - name: Deploy to the main repo
+        uses: peaceiris/actions-gh-pages@v3
+        if: ${{ github.event_name == 'push' }}
+        with:
+          deploy_key: ${{ secrets.ACTIONS_DEPLOY_KEY }}
+          external_repository: JuliaReinforcementLearning/JuliaReinforcementLearning.github.io
+          force_orphan: true
+          publish_branch: main
+          publish_dir: ./docs/homepage/__site

Project.toml

@@ -8,6 +8,7 @@ Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
 Reexport = "189a3867-3050-52da-a836-e630ba90ab69"
 ReinforcementLearningBase = "e575027e-6cd6-5018-9292-cdc6200d2b44"
 ReinforcementLearningCore = "de1b191a-4ae0-4afa-a27b-92d07f46b2d6"
+ReinforcementLearningDatasets = "dd1544ca-2576-438c-a599-ae96278fd687"
 ReinforcementLearningEnvironments = "25e41dd2-4622-11e9-1641-f1adca772921"
 ReinforcementLearningZoo = "d607f57d-ee1e-4ba7-bcf2-7734c1e31854"
 

docs/Project.toml

@@ -7,7 +7,6 @@ DemoCards = "311a05b2-6137-4a5a-b473-18580a3d38b5"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 Flux = "587475ba-b771-5e3f-ad9e-33799f191a9c"
-GridWorlds = "e15a9946-cd7f-4d03-83e2-6c30bacb0043"
 ImageTransformations = "02fcd773-0e25-5acc-982a-7f6622650795"
 InteractiveUtils = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 IntervalSets = "8197267c-284f-5f27-9208-e0e47529a953"
@@ -19,16 +18,11 @@ Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
 Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 PyPlot = "d330b81b-6aea-500a-939a-2ce795aea3ee"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-ReinforcementLearning = "158674fc-8238-5cab-b5ba-03dfc80d1318"
 ReinforcementLearningBase = "e575027e-6cd6-5018-9292-cdc6200d2b44"
 ReinforcementLearningCore = "de1b191a-4ae0-4afa-a27b-92d07f46b2d6"
-ReinforcementLearningDatasets = "dd1544ca-2576-438c-a599-ae96278fd687"
 ReinforcementLearningEnvironments = "25e41dd2-4622-11e9-1641-f1adca772921"
 ReinforcementLearningZoo = "d607f57d-ee1e-4ba7-bcf2-7734c1e31854"
 Setfield = "efcf1570-3423-57d1-acb7-fd33fddbac46"
 StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 TensorBoardLogger = "899adc3e-224a-11e9-021f-63837185c80f"
-
-[compat]
-GridWorlds = "0.5"

docs/make.jl

@@ -1,5 +1,6 @@
-using ReinforcementLearning
-using ReinforcementLearningDatasets
+# using ReinforcementLearning
+# using ReinforcementLearningDatasets
+using ReinforcementLearningCore, ReinforcementLearningBase, ReinforcementLearningZoo, ReinforcementLearningEnvironments
 using Documenter
 using Markdown
 using DemoCards
@@ -15,7 +16,17 @@ end
 
 exp_src_dir = joinpath(@__DIR__, "..", "src", "ReinforcementLearningExperiments", "deps", "experiments")
 exp_dest_dir = joinpath(@__DIR__, "experiments")
-cp(exp_src_dir, exp_dest_dir;force=true)
+cp(exp_src_dir, exp_dest_dir; force=true)
+
+# TODO: remove this as experiments are updated to run using latest RLCore
+# NOTE: config.json needs to be updated as well
+rm(joinpath(exp_dest_dir, "experiments", "CFR"), force=true, recursive=true)
+rm(joinpath(exp_dest_dir, "experiments", "DQN"), force=true, recursive=true)
+rm(joinpath(exp_dest_dir, "experiments", "ED"), force=true, recursive=true)
+rm(joinpath(exp_dest_dir, "experiments", "NFSP"), force=true, recursive=true)
+rm(joinpath(exp_dest_dir, "experiments", "Offline"), force=true, recursive=true)
+rm(joinpath(exp_dest_dir, "experiments", "Policy Gradient"), force=true, recursive=true)
+# rm(joinpath(exp_dest_dir, "experiments", "Search"), force=true, recursive=true)
 
 experiments, postprocess_cb, experiments_assets = makedemos("experiments")
 
@@ -27,12 +38,12 @@ assets = [
 
 makedocs(
     modules = [
-        ReinforcementLearning,
+        # ReinforcementLearning,
         ReinforcementLearningBase,
         ReinforcementLearningCore,
         ReinforcementLearningEnvironments,
         ReinforcementLearningZoo,
-        ReinforcementLearningDatasets,
+        # ReinforcementLearningDatasets,
     ],
     format = Documenter.HTML(
         prettyurls = true,
@@ -52,7 +63,7 @@ makedocs(
             "Episodic vs. Non-episodic environments" => "non_episodic.md",
         ],
         "Zoo Algorithms" => [
-            "MPO" => "src/Zoo Algorithms/MPO.md"
+            "MPO" => "Zoo_Algorithms/MPO.md"
         ],
         "FAQ" => "FAQ.md",
         experiments,

src/ReinforcementLearningExperiments/deps/build.jl

@@ -8,4 +8,4 @@ for (root, dirs, files) in walkdir(joinpath(@__DIR__, "experiments"))
             tangle(joinpath(root, f); informat="script", out_path=DEST_DIR)
         end
     end
-end
+end

src/ReinforcementLearningExperiments/deps/experiments/experiments/DQN/config.json

@@ -9,7 +9,7 @@
     "JuliaRL_PrioritizedDQN_CartPole.jl",
     "JuliaRL_DQN_MountainCar.jl",
     "JuliaRL_IQN_CartPole.jl",
-    "JuliaRL_QRDQN_Cartpole.jl",
+    "JuliaRL_QRDQN_CartPole.jl",
     "JuliaRL_REMDQN_CartPole.jl",
     "JuliaRL_Rainbow_CartPole.jl",
     "Dopamine_DQN_Atari.jl",

src/ReinforcementLearningExperiments/deps/experiments/experiments/Offline/GenDataset_BasicDQN_CartPole.jl

@@ -1,5 +1,6 @@
 # ---
 # title: GenDataset\_BasicDQN\_CartPole
+# cover: assets/logo.svg 
 # description: Collect CartPole dataset generated by BasicDQN
 # date: 2021-09-17
 # author: "[Guoyu Yang](https://github.com/pilgrimygy)"

src/ReinforcementLearningExperiments/deps/experiments/experiments/Offline/GenDataset_SAC_Pendulum.jl

@@ -1,5 +1,6 @@
 # ---
 # title: GenDataset\_SAC\_Pendulum
+# cover: assets/logo.svg 
 # description: Collect Pendulum dataset generated by SAC
 # date: 2021-09-17
 # author: "[Guoyu Yang](https://github.com/pilgrimygy)"

src/ReinforcementLearningExperiments/deps/experiments/experiments/Policy Gradient/JuliaRL_MPO_CartPole.jl

@@ -1,6 +1,6 @@
 # ---
 # title: JuliaRL\_MPO\_Cartpole
-# cover:
+# cover: assets/logo.svg
 # description: Solving Cartpole with MPO with a Discrete or a Continuous action space.
 # date: 2022-12-20
 # author: "[Henri Dehaybe](https://github.com/HenriDeh)"

src/ReinforcementLearningExperiments/deps/experiments/experiments/Policy Gradient/config.json

@@ -13,6 +13,8 @@
     "JuliaRL_TD3_Pendulum.jl",
     "JuliaRL_VMPO_CartPole.jl",
     "JuliaRL_VPG_CartPole.jl",
+    "JuliaRL_MPO_CartPole.jl",
+    "JuliaRL_TRPO_CartPole.jl",    
     "rlpyt_A2C_Atari.jl",
     "rlpyt_PPO_Atari.jl"
   ]

src/ReinforcementLearningExperiments/deps/experiments/experiments/config.json

@@ -1,12 +1,6 @@
 {
   "order": [
-    "DQN",
-    "Policy Gradient",
-    "Offline",
-    "Search",
-    "CFR",
-    "NFSP",
-    "ED"
+    "Search"
   ]
 }