diff --git a/docs/index.rst b/docs/index.rst index 009e9eb96..6a82e6d52 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -94,6 +94,7 @@ Tianshou is still under development, you can also check out the documents in sta :maxdepth: 1 :caption: Tutorials + tutorials/get_started tutorials/dqn tutorials/concepts tutorials/batch diff --git a/docs/spelling_wordlist.txt b/docs/spelling_wordlist.txt index 8a8f9755a..b334e1db9 100644 --- a/docs/spelling_wordlist.txt +++ b/docs/spelling_wordlist.txt @@ -147,3 +147,6 @@ mse gail airl ppo +Jupyter +Colab +Colaboratory diff --git a/docs/tutorials/get_started.rst b/docs/tutorials/get_started.rst new file mode 100644 index 000000000..08e386a3b --- /dev/null +++ b/docs/tutorials/get_started.rst @@ -0,0 +1,13 @@ +Get Started with Jupyter Notebook +================================= + +In this tutorial, we will use Google Colaboratory to show you the most basic usages of common building blocks in Tianshou. You will be guided step by step to see how different modules in Tianshou collaborate with each other to conduct a classic DRL experiment (PPO algorithm for CartPole-v0 environment). + +- L0: `Overview `_ +- L1: `Batch `_ +- L2: `Replay Buffer `_ +- L3: `Vectorized Environment `_ +- L4: `Policy `_ +- L5: `Collector `_ +- L6: `Trainer `_ +- L7: `Experiment `_