AgileRL curriculum learning and self-play tutorial

.github/workflows/docs-test.yml

@@ -35,4 +35,4 @@ jobs:
               run: python docs/_scripts/gen_envs_mds.py
             - name: Documentation test
               run: |
-                  xvfb-run -s "-screen 0 1024x768x24" pytest docs --markdown-docs -m markdown-docs --splits 10 --group ${{ matrix.group }}
+                  xvfb-run -s "-screen 0 1024x768x24" pytest docs --markdown-docs -m markdown-docs --ignore=tutorials --ignore=docs/tutorials --splits 10 --group ${{ matrix.group }}

.github/workflows/linux-tutorials-test.yml

@@ -17,7 +17,7 @@ jobs:
             fail-fast: false
             matrix:
                 python-version: ['3.8', '3.9', '3.10', '3.11']
-                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test] # TODO: add back AgileRL once issue is fixed on their end
+                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test, AgileRL]  # TODO: add back Ray once next release after 2.6.2
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

docs/tutorials/agilerl/index.md

@@ -2,6 +2,7 @@
 
 These tutorials provide an introductory guide to using [AgileRL](https://github.com/AgileRL/AgileRL) with PettingZoo. AgileRL's multi-agent algorithms make use of the PettingZoo parallel API and allow users to train multiple-agents in parallel in both competitive and co-operative environments. This tutorial includes the following:
 
+* [DQN](DQN.md): _Train a DQN agent to play Connect Four through curriculum learning and self-play_
 * [MADDPG](MADDPG.md): _Train an MADDPG agent to play multi-agent atari games_
 * [MATD3](MATD3.md): _Train an MATD3 agent to play multi-particle-environment games_
 
@@ -28,6 +29,7 @@ For more information about AgileRL and what else the library has to offer, check
 :hidden:
 :caption: AgileRL
 
+DQN
 MADDPG
 MATD3
 ```