Add docs publishing pipeline and switch back to poetry

.buildkite/pipeline.yml

@@ -0,0 +1,18 @@
+common: &common
+  plugins:
+  - EmbarkStudios/k8s#1.2.10:
+      service-account-name: monorepo-ci
+      image: gcr.io/embark-shared/ml/monorepo-controller@sha256:aad8ab820105ea1c0dea9dad53b1d1853b92eee93a4a7e3663fe0b265806fa8c
+      default-secret-name: buildkite-k8s-plugin
+      always-pull: true
+
+  agents:
+    cluster: builds-fi-2
+    queue: monorepo-ci
+    size: small
+
+steps:
+  - label: 📚 Publish docs
+    command: bash .buildkite/publish-docs.sh
+
+    << : *common

.buildkite/publish-docs.sh

@@ -0,0 +1,39 @@
+set -eo pipefail
+
+echo --- Installing dependencies
+
+apt-get update \
+    && apt-get install --no-install-recommends -y \
+        curl \
+        build-essential
+
+export PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=off \
+    PIP_DISABLE_PIP_VERSION_CHECK=on \
+    PIP_DEFAULT_TIMEOUT=100 \
+    POETRY_VERSION=1.2.0b1 \
+    POETRY_HOME="/tmp/poetry" \
+    POETRY_VIRTUALENVS_IN_PROJECT=true \
+    POETRY_NO_INTERACTION=1 \
+
+pip install poetry==1.2.0b1
+poetry install
+poetry env info --path
+
+
+echo --- Initializing gcloud
+
+curl https://sdk.cloud.google.com > install.sh && \
+    bash install.sh --disable-prompts 2>&1 && \
+    /root/google-cloud-sdk/install.sh --path-update true --usage-reporting false --quiet
+
+if [ -f '/root/google-cloud-sdk/path.bash.inc' ]; then . '/root/google-cloud-sdk/path.bash.inc'; fi
+gcloud config set account monorepo-ci@embark-builds.iam.gserviceaccount.com
+
+echo --- Building docs
+pushd docs
+poetry env info --path
+make deploy
+gsutil rsync -r ./_build/dirhtml gs://embark-static/emote-docs
+popd

.gitignore

@@ -1,8 +1,17 @@
-__pycache__/
-.vscode
-.dir-locals.el
-*.egg-info
-*.onnx
-.coverage
-docs/_build
-runs/**
+# Miscellaneous editor files
+.vscode
+.dir-locals.el
+
+# Output from Python and Python tools
+__pycache__/
+*.egg-info
+.coverage
+
+# Files generated by the docs publishing systems
+docs/_build
+docs/generated
+docs/coverage.rst
+
+# Outputs from Emote and tests
+*.onnx
+runs/**

README.md

@@ -1,141 +1,144 @@
-<!-- Allow this file to not have a first line heading -->
-<!-- markdownlint-disable-file MD041 -->
-
-<!-- inline html -->
-<!-- markdownlint-disable-file MD033 -->
-
-<div align="center">
-
-# `🍒 emote`
-
-**E**mbark's **Mo**dular **T**raining **E**ngine - a flexible framework for
-reinforcement learning 
-
-[![Embark](https://img.shields.io/badge/embark-open%20source-blueviolet.svg)](https://embark.dev)
-[![Embark](https://img.shields.io/badge/discord-ark-%237289da.svg?logo=discord)](https://discord.gg/dAuKfZS)
-[![Documentation Status](https://readthedocs.org/projects/emote/badge/?version=latest)](http://emote.readthedocs.io/?badge=latest)
-[![PyPI version fury.io](https://badge.fury.io/py/emote.svg)](https://pypi.python.org/pypi/emote/)
-[![Build status](https://github.com/EmbarkStudios/emote/workflows/CI/badge.svg)](https://github.com/EmbarkStudios/emote/actions)
-
-🚧 This project is very much **work in progress and not yet ready for production use.** 🚧
-
-</div>
-
-
-## What it does
-
-Emote provides a way to build reusable components for creating reinforcement learning algorithms, and a
-library of premade componenents built in this way. It is strongly inspired by the callback setup used
-by Keras and FastAI.
-
-As an example, let us see how the SAC, the Soft Actor Critic algorithm by
-[Haarnoja et al.](https://arxiv.org/abs/1801.01290) can be written using Emote. The main algorithm in
-SAC is given in [Soft Actor-Critic Algorithms and Applications](https://arxiv.org/abs/1812.05905) and
-looks like this:
-
-<div align="center">
-
-![Main SAC algorithm](./docs/haarnoja_sac.png)
-
-</div>
-
-Using the components provided with Emote, we can write this as
-
-```python
-env = DictGymWrapper(AsyncVectorEnv(10 * [HitTheMiddle]))
-table = DictObsTable(spaces=env.dict_space, maxlen=1000)
-memory_proxy = TableMemoryProxy(table)
-dataloader = MemoryLoader(table, 100, 2, "batch_size")
-
-q1 = QNet(2, 1)
-q2 = QNet(2, 1)
-policy = Policy(2, 1)
-ln_alpha = torch.tensor(1.0, requires_grad=True)
-agent_proxy = FeatureAgentProxy(policy)
-
-callbacks = [
-    QLoss(name="q1", q=q1, opt=Adam(q1.parameters(), lr=8e-3)),
-    QLoss(name="q2", q=q2, opt=Adam(q2.parameters(), lr=8e-3)),
-    PolicyLoss(pi=policy, ln_alpha=ln_alpha, q=q1, opt=Adam(policy.parameters())),
-    AlphaLoss(pi=policy, ln_alpha=ln_alpha, opt=Adam([ln_alpha]), n_actions=1),
-    QTarget(pi=policy, ln_alpha=ln_alpha, q1=q1, q2=q2),
-    SimpleGymCollector(env, agent_proxy, memory_proxy, warmup_steps=500),
-    FinalLossTestCheck([logged_cbs[2]], [10.0], 2000),
-]
-
-trainer = Trainer(callbacks, dataloader)
-trainer.train()
-```
-
-Here each callback in the `callbacks` list is its own reusable class that can readily be used
-for other similar algorithms. The callback classes themselves are very straight forward to write.
-As an example, here is the `PolicyLoss` callback.
-
-```python
-class PolicyLoss(LossCallback):
-    def __init__(
-        self,
-        *,
-        pi: nn.Module,
-        ln_alpha: torch.tensor,
-        q: nn.Module,
-        opt: optim.Optimizer,
-        max_grad_norm: float = 10.0,
-        name: str = "policy",
-        data_group: str = "default",
-    ):
-        super().__init__(
-            name=name,
-            optimizer=opt,
-            network=pi,
-            max_grad_norm=max_grad_norm,
-            data_group=data_group,
-        )
-        self.policy = pi
-        self._ln_alpha = ln_alpha
-        self.q1 = q
-        self.q2 = q2
-
-    def loss(self, observation):
-        p_sample, logp_pi = self.policy(**observation)
-        q_pi_min = self.q1(p_sample, **observation)
-        # using reparameterization trick
-        alpha = torch.exp(self._ln_alpha).detach()
-        policy_loss = alpha * logp_pi - q_pi_min
-        policy_loss = torch.mean(policy_loss)
-        assert policy_loss.dim() == 0
-        return policy_loss
-```
-
-## Installation
-
-For installation and environment handling we use `conda`. Install it from [here](https://docs.anaconda.com/anaconda/install/). After `conda` is set up, set up and activate the emote environment by running
-
-```bash
-conda env create -f environment.yml
-conda activate emote
-pip install -r pip-requirements.txt
-```
-
-
-## Contribution
-
-[![Contributor Covenant](https://img.shields.io/badge/contributor%20covenant-v1.4-ff69b4.svg)](../main/CODE_OF_CONDUCT.md)
-
-We welcome community contributions to this project.
-
-Please read our [Contributor Guide](CONTRIBUTING.md) for more information on how to get started.
-Please also read our [Contributor Terms](CONTRIBUTING.md#contributor-terms) before you make any contributions.
-
-Any contribution intentionally submitted for inclusion in an Embark Studios project, shall comply with the Rust standard licensing model (MIT OR Apache 2.0) and therefore be dual licensed as described below, without any additional terms or conditions:
-
-### License
-
-This contribution is dual licensed under EITHER OF
-
-* Apache License, Version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or <http://www.apache.org/licenses/LICENSE-2.0>)
-* MIT license ([LICENSE-MIT](LICENSE-MIT) or <http://opensource.org/licenses/MIT>)
-
-at your option.
-
-For clarity, "your" refers to Embark or any other licensee/user of the contribution.
+<!-- Allow this file to not have a first line heading -->
+<!-- markdownlint-disable-file MD041 -->
+
+<!-- inline html -->
+<!-- markdownlint-disable-file MD033 -->
+
+<div align="center">
+
+# `🍒 emote`
+
+**E**mbark's **Mo**dular **T**raining **E**ngine - a flexible framework for
+reinforcement learning 
+
+[![Embark](https://img.shields.io/badge/embark-open%20source-blueviolet.svg)](https://embark.dev)
+[![Embark](https://img.shields.io/badge/discord-ark-%237289da.svg?logo=discord)](https://discord.gg/dAuKfZS)
+[![Build status](https://badge.buildkite.com/968ac3c0bb075fb878f9f973ed91406c8b257b0f050c197542.svg?theme=github&branch=ts/docs-poetry)](https://buildkite.com/embark-studios/emote)
+[![Docs status](https://img.shields.io/badge/Docs-latest-brightgreen)](https://static.embark.net/emote-docs/)
+
+🚧 This project is very much **work in progress and not yet ready for production use.** 🚧
+
+</div>
+
+
+## What it does
+
+Emote provides a way to build reusable components for creating reinforcement learning algorithms, and a
+library of premade componenents built in this way. It is strongly inspired by the callback setup used
+by Keras and FastAI.
+
+As an example, let us see how the SAC, the Soft Actor Critic algorithm by
+[Haarnoja et al.](https://arxiv.org/abs/1801.01290) can be written using Emote. The main algorithm in
+SAC is given in [Soft Actor-Critic Algorithms and Applications](https://arxiv.org/abs/1812.05905) and
+looks like this:
+
+<div align="center">
+
+![Main SAC algorithm](./docs/haarnoja_sac.png)
+
+</div>
+
+Using the components provided with Emote, we can write this as
+
+```python
+env = DictGymWrapper(AsyncVectorEnv(10 * [HitTheMiddle]))
+table = DictObsTable(spaces=env.dict_space, maxlen=1000)
+memory_proxy = TableMemoryProxy(table)
+dataloader = MemoryLoader(table, 100, 2, "batch_size")
+
+q1 = QNet(2, 1)
+q2 = QNet(2, 1)
+policy = Policy(2, 1)
+ln_alpha = torch.tensor(1.0, requires_grad=True)
+agent_proxy = FeatureAgentProxy(policy)
+
+callbacks = [
+    QLoss(name="q1", q=q1, opt=Adam(q1.parameters(), lr=8e-3)),
+    QLoss(name="q2", q=q2, opt=Adam(q2.parameters(), lr=8e-3)),
+    PolicyLoss(pi=policy, ln_alpha=ln_alpha, q=q1, opt=Adam(policy.parameters())),
+    AlphaLoss(pi=policy, ln_alpha=ln_alpha, opt=Adam([ln_alpha]), n_actions=1),
+    QTarget(pi=policy, ln_alpha=ln_alpha, q1=q1, q2=q2),
+    SimpleGymCollector(env, agent_proxy, memory_proxy, warmup_steps=500),
+    FinalLossTestCheck([logged_cbs[2]], [10.0], 2000),
+]
+
+trainer = Trainer(callbacks, dataloader)
+trainer.train()
+```
+
+Here each callback in the `callbacks` list is its own reusable class that can readily be used
+for other similar algorithms. The callback classes themselves are very straight forward to write.
+As an example, here is the `PolicyLoss` callback.
+
+```python
+class PolicyLoss(LossCallback):
+    def __init__(
+        self,
+        *,
+        pi: nn.Module,
+        ln_alpha: torch.tensor,
+        q: nn.Module,
+        opt: optim.Optimizer,
+        max_grad_norm: float = 10.0,
+        name: str = "policy",
+        data_group: str = "default",
+    ):
+        super().__init__(
+            name=name,
+            optimizer=opt,
+            network=pi,
+            max_grad_norm=max_grad_norm,
+            data_group=data_group,
+        )
+        self.policy = pi
+        self._ln_alpha = ln_alpha
+        self.q1 = q
+        self.q2 = q2
+
+    def loss(self, observation):
+        p_sample, logp_pi = self.policy(**observation)
+        q_pi_min = self.q1(p_sample, **observation)
+        # using reparameterization trick
+        alpha = torch.exp(self._ln_alpha).detach()
+        policy_loss = alpha * logp_pi - q_pi_min
+        policy_loss = torch.mean(policy_loss)
+        assert policy_loss.dim() == 0
+        return policy_loss
+```
+
+## Installation
+
+:warning: Due to bugs in Poetry you currently need to use one of the pre-release versions of the 1.2 series. :warning:
+
+For installation and environment handling we use `poetry`. Install it from [here](https://python-poetry.org/). After `poetry` is set up, set up and activate the emote environment by running
+
+
+
+```bash
+poetry install
+```
+
+
+
+
+## Contribution
+
+[![Contributor Covenant](https://img.shields.io/badge/contributor%20covenant-v1.4-ff69b4.svg)](../main/CODE_OF_CONDUCT.md)
+
+We welcome community contributions to this project.
+
+Please read our [Contributor Guide](CONTRIBUTING.md) for more information on how to get started.
+Please also read our [Contributor Terms](CONTRIBUTING.md#contributor-terms) before you make any contributions.
+
+Any contribution intentionally submitted for inclusion in an Embark Studios project, shall comply with the Rust standard licensing model (MIT OR Apache 2.0) and therefore be dual licensed as described below, without any additional terms or conditions:
+
+### License
+
+This contribution is dual licensed under EITHER OF
+
+* Apache License, Version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or <http://www.apache.org/licenses/LICENSE-2.0>)
+* MIT license ([LICENSE-MIT](LICENSE-MIT) or <http://opensource.org/licenses/MIT>)
+
+at your option.
+
+For clarity, "your" refers to Embark or any other licensee/user of the contribution.

docs/Makefile

@@ -3,8 +3,8 @@
 
 # You can set these variables from the command line, and also
 # from the environment for the first two.
-SPHINXOPTS    ?=
-SPHINXBUILD   ?= sphinx-build
+SPHINXOPTS    ?= 
+SPHINXBUILD   ?= poetry run sphinx-build
 SOURCEDIR     = .
 BUILDDIR      = _build
 
@@ -18,3 +18,8 @@ help:
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
 	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+deploy:
+	@$(SPHINXBUILD) -M coverage "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 
+	cp "$(BUILDDIR)/coverage/python.txt" "$(SOURCEDIR)/coverage.rst"
+	@$(SPHINXBUILD) -M dirhtml "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)