mirror of
https://github.com/microsoft/qlib.git
synced 2026-06-06 05:51:17 +08:00
7f1e8c5206
* wip * wip * wip * Fix naming errors * Backtest test passed * Why training stuck? * Minor * Refine train configs * Use dummy in training * Remove pickle_dataframe * CI * CI * Add more strict condition to filter orders * Pass test * Add TODO in example --------- Co-authored-by: Young <afe.young@gmail.com>
68 lines
1.7 KiB
YAML
Executable File
68 lines
1.7 KiB
YAML
Executable File
simulator:
|
|
data_granularity: 5
|
|
time_per_step: 30
|
|
vol_limit: null
|
|
env:
|
|
concurrency: 32
|
|
parallel_mode: dummy
|
|
action_interpreter:
|
|
class: CategoricalActionInterpreter
|
|
kwargs:
|
|
values: 4
|
|
max_step: 8
|
|
module_path: qlib.rl.order_execution.interpreter
|
|
state_interpreter:
|
|
class: FullHistoryStateInterpreter
|
|
kwargs:
|
|
data_dim: 5
|
|
data_ticks: 48 # 48 = 240 min / 5 min
|
|
max_step: 8
|
|
processed_data_provider:
|
|
class: HandlerProcessedDataProvider
|
|
kwargs:
|
|
data_dir: ./data/pickle/
|
|
feature_columns_today: ["$high", "$low", "$open", "$close", "$volume"]
|
|
feature_columns_yesterday: ["$high_1", "$low_1", "$open_1", "$close_1", "$volume_1"]
|
|
backtest: false
|
|
module_path: qlib.rl.data.native
|
|
module_path: qlib.rl.order_execution.interpreter
|
|
reward:
|
|
class: PPOReward
|
|
kwargs:
|
|
max_step: 8
|
|
start_time_index: 0
|
|
end_time_index: 46 # 46 = (240 - 5) min / 5 min - 1
|
|
module_path: qlib.rl.order_execution.reward
|
|
data:
|
|
source:
|
|
order_dir: ./data/orders
|
|
feature_root_dir: ./data/pickle/
|
|
feature_columns_today: ["$close0", "$volume0"]
|
|
feature_columns_yesterday: []
|
|
total_time: 240
|
|
default_start_time_index: 0
|
|
default_end_time_index: 235
|
|
proc_data_dim: 5
|
|
num_workers: 0
|
|
queue_size: 20
|
|
network:
|
|
class: Recurrent
|
|
module_path: qlib.rl.order_execution.network
|
|
policy:
|
|
class: PPO # PPO, DQN
|
|
kwargs:
|
|
lr: 0.0001
|
|
module_path: qlib.rl.order_execution.policy
|
|
runtime:
|
|
seed: 42
|
|
use_cuda: false
|
|
trainer:
|
|
max_epoch: 500
|
|
repeat_per_collect: 25
|
|
earlystop_patience: 50
|
|
episode_per_collect: 10000
|
|
batch_size: 1024
|
|
val_every_n_epoch: 4
|
|
checkpoint_path: ./outputs/ppo
|
|
checkpoint_every_n_iters: 1
|