Add docs for qlib.rl (#1322)

* Add docs for qlib.rl

* Update docs for qlib.rl

* Add homepage introduct to RL framework

* Update index Link

* Fix Icon

* typo

* Update catelog

* Update docs for qlib.rl

* Update docs for qlib.rl

* Update figure

* Update docs for qlib.rl

* Update setup.py

* FIx setup.py

* Update docs and fix some typos

* Fix the reference to RL docs

* Update framework.svg

* Update framework.svg

* Update framework.svg

* Update docs for qlibrl.

* Update docs for qlibrl.

* Update docs for Qlibrl.

* Update docs for qlibrl.

* Update docs for qlibrl.

* Update docs for qlibrl.

* Add new framework

* Update jpg

* Update framework.svg

* Update framework.svg

* Update Qlib framework and description

* Update grammar

* Update README.md

* Update README.md

* Update docs/component/rl.rst

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

* Update docs/component/rl.rst

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

* Update docs for qlib.rl

* Change theme for docs.

* Update docs for qlib.rl

* Update docs for qlib.rl

* Update docs for qlib.rl

* Update docs for qlib.rl.

* Update docs for qlib.rl

* Update docs for qlib.rl

* Update docs for qlib.rl

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

qlib/rl/__init__.py

@@ -1,2 +1,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
+
+from .interpreter import Interpreter, StateInterpreter, ActionInterpreter
+from .reward import Reward, RewardCombination
+from .simulator import Simulator
+
+__all__ = ["Interpreter", "StateInterpreter", "ActionInterpreter", "Reward", "RewardCombination", "Simulator"]

qlib/rl/order_execution/__init__.py

@@ -6,8 +6,33 @@ Currently it supports single-asset order execution.
 Multi-asset is on the way.
 """
 
-from .interpreter import *
-from .network import *
-from .policy import *
-from .reward import *
-from .simulator_simple import *
+from .interpreter import (
+    FullHistoryStateInterpreter,
+    CurrentStepStateInterpreter,
+    CategoricalActionInterpreter,
+    TwapRelativeActionInterpreter,
+)
+from .network import Recurrent
+from .policy import AllOne, PPO
+from .reward import PAPenaltyReward
+from .simulator_simple import SingleAssetOrderExecutionSimple
+from .state import SAOEStateAdapter, SAOEMetrics, SAOEState
+from .strategy import SAOEStrategy, ProxySAOEStrategy, SAOEIntStrategy
+
+__all__ = [
+    "FullHistoryStateInterpreter",
+    "CurrentStepStateInterpreter",
+    "CategoricalActionInterpreter",
+    "TwapRelativeActionInterpreter",
+    "Recurrent",
+    "AllOne",
+    "PPO",
+    "PAPenaltyReward",
+    "SingleAssetOrderExecutionSimple",
+    "SAOEStateAdapter",
+    "SAOEMetrics",
+    "SAOEState",
+    "SAOEStrategy",
+    "ProxySAOEStrategy",
+    "SAOEIntStrategy",
+]

qlib/rl/strategy/__init__.py

@@ -1,2 +1,5 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
+from .single_order import SingleOrderStrategy
+
+__all__ = ["SingleOrderStrategy"]

qlib/rl/trainer/__init__.py

@@ -7,3 +7,5 @@ from .api import backtest, train
 from .callbacks import Checkpoint, EarlyStopping
 from .trainer import Trainer
 from .vessel import TrainingVessel, TrainingVesselBase
+
+__all__ = ["Trainer", "TrainingVessel", "TrainingVesselBase", "Checkpoint", "EarlyStopping", "train", "backtest"]