mirror of
https://github.com/microsoft/qlib.git
synced 2026-06-06 05:51:17 +08:00
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>
This commit is contained in:
Lewen Wang
@@ -41,7 +41,7 @@ data
|
||||
Run:
|
||||
|
||||
```
|
||||
python ../../qlib/rl/contrib/train_onpolicy.py --config_path ./experiment_config/training/config.yml
|
||||
python -m qlib.rl.contrib.train_onpolicy.py --config_path ./experiment_config/training/config.yml
|
||||
```
|
||||
|
||||
After training, checkpoints will be stored under `checkpoints/`.
|
||||
@@ -49,7 +49,7 @@ After training, checkpoints will be stored under `checkpoints/`.
|
||||
## Run backtest
|
||||
|
||||
```
|
||||
python ../../qlib/rl/contrib/backtest.py --config_path ./experiment_config/backtest/config.py
|
||||
python -m qlib.rl.contrib.backtest.py --config_path ./experiment_config/backtest/config.yml
|
||||
```
|
||||
|
||||
The backtest workflow will use the trained model in `checkpoints/`. The backtest summary can be found in `outputs/`.
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
_base_ = ["./twap.yml"]
|
||||
|
||||
strategies = {
|
||||
"_delete_": True,
|
||||
"30min": {
|
||||
"class": "TWAPStrategy",
|
||||
"module_path": "qlib.contrib.strategy.rule_strategy",
|
||||
"kwargs": {},
|
||||
},
|
||||
"1day": {
|
||||
"class": "SAOEIntStrategy",
|
||||
"module_path": "qlib.rl.order_execution.strategy",
|
||||
"kwargs": {
|
||||
"state_interpreter": {
|
||||
"class": "FullHistoryStateInterpreter",
|
||||
"module_path": "qlib.rl.order_execution.interpreter",
|
||||
"kwargs": {
|
||||
"max_step": 8,
|
||||
"data_ticks": 240,
|
||||
"data_dim": 6,
|
||||
"processed_data_provider": {
|
||||
"class": "PickleProcessedDataProvider",
|
||||
"module_path": "qlib.rl.data.pickle_styled",
|
||||
"kwargs": {
|
||||
"data_dir": "./data/pickle_dataframe/feature",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
"action_interpreter": {
|
||||
"class": "CategoricalActionInterpreter",
|
||||
"module_path": "qlib.rl.order_execution.interpreter",
|
||||
"kwargs": {
|
||||
"values": 14,
|
||||
"max_step": 8,
|
||||
},
|
||||
},
|
||||
"network": {
|
||||
"class": "Recurrent",
|
||||
"module_path": "qlib.rl.order_execution.network",
|
||||
"kwargs": {},
|
||||
},
|
||||
"policy": {
|
||||
"class": "PPO",
|
||||
"module_path": "qlib.rl.order_execution.policy",
|
||||
"kwargs": {
|
||||
"lr": 1.0e-4,
|
||||
"weight_file": "./checkpoints/latest.pth",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
57
examples/rl/experiment_config/backtest/config.yml
Normal file
57
examples/rl/experiment_config/backtest/config.yml
Normal file
@@ -0,0 +1,57 @@
|
||||
order_file: ./data/backtest_orders.csv
|
||||
start_time: "9:45"
|
||||
end_time: "14:44"
|
||||
qlib:
|
||||
provider_uri_1min: ./data/bin
|
||||
feature_root_dir: ./data/pickle
|
||||
feature_columns_today: [
|
||||
"$open", "$high", "$low", "$close", "$vwap", "$volume",
|
||||
]
|
||||
feature_columns_yesterday: [
|
||||
"$open_v1", "$high_v1", "$low_v1", "$close_v1", "$vwap_v1", "$volume_v1",
|
||||
]
|
||||
exchange:
|
||||
limit_threshold: ['$close == 0', '$close == 0']
|
||||
deal_price: ["If($close == 0, $vwap, $close)", "If($close == 0, $vwap, $close)"]
|
||||
volume_threshold:
|
||||
all: ["cum", "0.2 * DayCumsum($volume, '9:45', '14:44')"]
|
||||
buy: ["current", "$close"]
|
||||
sell: ["current", "$close"]
|
||||
strategies:
|
||||
30min:
|
||||
class: TWAPStrategy
|
||||
module_path: qlib.contrib.strategy.rule_strategy
|
||||
kwargs: {}
|
||||
1day:
|
||||
class: SAOEIntStrategy
|
||||
module_path: qlib.rl.order_execution.strategy
|
||||
kwargs:
|
||||
state_interpreter:
|
||||
class: FullHistoryStateInterpreter
|
||||
module_path: qlib.rl.order_execution.interpreter
|
||||
kwargs:
|
||||
max_step: 8
|
||||
data_ticks: 240
|
||||
data_dim: 6
|
||||
processed_data_provider:
|
||||
class: PickleProcessedDataProvider
|
||||
module_path: qlib.rl.data.pickle_styled
|
||||
kwargs:
|
||||
data_dir: ./data/pickle_dataframe/feature
|
||||
action_interpreter:
|
||||
class: CategoricalActionInterpreter
|
||||
module_path: qlib.rl.order_execution.interpreter
|
||||
kwargs:
|
||||
values: 14
|
||||
max_step: 8
|
||||
network:
|
||||
class: Recurrent
|
||||
module_path: qlib.rl.order_execution.network
|
||||
kwargs: {}
|
||||
policy:
|
||||
class: PPO
|
||||
module_path: qlib.rl.order_execution.policy
|
||||
kwargs:
|
||||
lr: 1.0e-4
|
||||
weight_file: ./checkpoints/latest.pth
|
||||
concurrency: 5
|
||||
@@ -1,21 +0,0 @@
|
||||
order_file: ./data/backtest_orders.csv
|
||||
start_time: "9:45"
|
||||
end_time: "14:44"
|
||||
qlib:
|
||||
provider_uri_1min: ./data/bin
|
||||
feature_root_dir: ./data/pickle
|
||||
feature_columns_today: [
|
||||
"$open", "$high", "$low", "$close", "$vwap", "$volume",
|
||||
]
|
||||
feature_columns_yesterday: [
|
||||
"$open_v1", "$high_v1", "$low_v1", "$close_v1", "$vwap_v1", "$volume_v1",
|
||||
]
|
||||
exchange:
|
||||
limit_threshold: ['$close == 0', '$close == 0']
|
||||
deal_price: ["If($close == 0, $vwap, $close)", "If($close == 0, $vwap, $close)"]
|
||||
volume_threshold:
|
||||
all: ["cum", "0.2 * DayCumsum($volume, '9:45', '14:44')"]
|
||||
buy: ["current", "$close"]
|
||||
sell: ["current", "$close"]
|
||||
strategies: {} # Placeholder
|
||||
concurrency: 5
|
||||
Reference in New Issue
Block a user