快速开始

QlibRL 提供了一个单资产订单执行任务的实现示例，以下是用于使用 QlibRL 进行训练的配置文件示例。

simulator:
    # Each step contains 30mins
    time_per_step: 30
    # Upper bound of volume, should be null or a float between 0 and 1, if it is a float, represent upper bound is calculated by the percentage of the market volume
    vol_limit: null
env:
    # Concurrent environment workers.
    concurrency: 1
    # dummy or subproc or shmem. Corresponding to `parallelism in tianshou <https://tianshou.readthedocs.io/en/master/api/tianshou.env.html#vectorenv>`_.
    parallel_mode: dummy
action_interpreter:
    class: CategoricalActionInterpreter
    kwargs:
        # Candidate actions, it can be a list with length L: [a_1, a_2,..., a_L] or an integer n, in which case the list of length n+1 is auto-generated, i.e., [0, 1/n, 2/n,..., n/n].
        values: 14
        # Total number of steps (an upper-bound estimation)
        max_step: 8
    module_path: qlib.rl.order_execution.interpreter
state_interpreter:
    class: FullHistoryStateInterpreter
    kwargs:
        # Number of dimensions in data.
        data_dim: 6
        # Equal to the total number of records. For example, in SAOE per minute, data_ticks is the length of the day in minutes.
        data_ticks: 240
        # The total number of steps (an upper-bound estimation). For example, 390min / 30min-per-step = 13 steps.
        max_step: 8
        # Provider of the processed data.
        processed_data_provider:
            class: PickleProcessedDataProvider
            module_path: qlib.rl.data.pickle_styled
            kwargs:
                data_dir: ./data/pickle_dataframe/feature
    module_path: qlib.rl.order_execution.interpreter
reward:
    class: PAPenaltyReward
    kwargs:
        # The penalty for a large volume in a short time.
        penalty: 100.0
    module_path: qlib.rl.order_execution.reward
data:
    source:
        order_dir: ./data/training_order_split
        data_dir: ./data/pickle_dataframe/backtest
        # number of time indexes
        total_time: 240
        # start time index
        default_start_time: 0
        # end time index
        default_end_time: 240
        proc_data_dim: 6
    num_workers: 0
    queue_size: 20
network:
    class: Recurrent
    module_path: qlib.rl.order_execution.network
policy:
    class: PPO
    kwargs:
        lr: 0.0001
    module_path: qlib.rl.order_execution.policy
runtime:
    seed: 42
    use_cuda: false
trainer:
    max_epoch: 2
    # Number of episodes collected in each training iteration
    repeat_per_collect: 5
    earlystop_patience: 2
    # Episodes per collect at training.
    episode_per_collect: 20
    batch_size: 16
    # Perform validation every n iterations
    val_every_n_epoch: 1
    checkpoint_path: ./checkpoints
    checkpoint_every_n_iters: 1

回测的配置文件如下：

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 generated by today's information
    feature_columns_today: [
        "$open", "$high", "$low", "$close", "$vwap", "$volume",
    ]
    # feature generated by yesterday's information
    feature_columns_yesterday: [
        "$open_v1", "$high_v1", "$low_v1", "$close_v1", "$vwap_v1", "$volume_v1",
    ]
exchange:
    # the expression for buying and selling stock limitation
    limit_threshold: ['$close == 0', '$close == 0']
    # deal price for buying and selling
    deal_price: ["If($close == 0, $vwap, $close)", "If($close == 0, $vwap, $close)"]
volume_threshold:
    # volume limits are both buying and selling, "cum" means that this is a cumulative value over time
    all: ["cum", "0.2 * DayCumsum($volume, '9:45', '14:44')"]
    # the volume limits of buying
    buy: ["current", "$close"]
    # the volume limits of selling, "current" means that this is a real-time value and will not accumulate over time
    sell: ["current", "$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
                # Local path to the latest model. The model is generated during training, so please run training first if you want to run backtest with a trained policy. You could also remove this parameter file to run backtest with a randomly initialized policy.
                weight_file: ./checkpoints/latest.pth
# Concurrent environment workers.
concurrency: 5

使用上述配置文件，您可以通过以下命令启动训练：

$ python -m qlib.rl.contrib.train_onpolicy.py --config_path train_config.yml

训练完成后，您可以通过以下命令进行回测：

$ python -m qlib.rl.contrib.backtest.py --config_path backtest_config.yml

在此示例中，SingleAssetOrderExecution 和 SingleAssetOrderExecutionSimple 作为模拟器的示例，qlib.rl.order_execution.interpreter.FullHistoryStateInterpreter 和 qlib.rl.order_execution.interpreter.CategoricalActionInterpreter 作为解释器的示例，qlib.rl.order_execution.policy.PPO 作为策略的示例，qlib.rl.order_execution.reward.PAPenaltyReward 作为奖励函数的示例。对于单资产订单执行任务，如果开发者已定义了自己的模拟器/解释器/奖励函数/策略，只需修改配置文件中的相应设置即可启动训练和回测流程。有关此示例的详细信息，请参阅此处。

未来，我们将提供更多针对不同场景的示例，例如基于强化学习的投资组合构建。