diff --git a/examples/rl/README.md b/examples/rl/README.md
deleted file mode 100644
index e4b4488d08..0000000000
--- a/examples/rl/README.md
+++ /dev/null
@@ -1,60 +0,0 @@
-This folder contains a simple example of how to run Qlib RL. It contains:
-
-```
-.
-├── experiment_config
-│   ├── backtest       # Backtest config
-│   └── training       # Training config
-├── README.md          # Readme (the current file)
-└── scripts            # Scripts for data pre-processing
-```
-
-## Data preparation
-
-Use [AzCopy](https://learn.microsoft.com/en-us/azure/storage/common/storage-use-azcopy-v10) to download data:
-
-```
-azcopy copy https://qlibpublic.blob.core.windows.net/data/rl/qlib_rl_example_data ./ --recursive
-mv qlib_rl_example_data data
-```
-
-The downloaded data will be placed at `./data`. The original data are in `data/csv`. To create all data needed by the case, run:
-
-```
-bash scripts/data_pipeline.sh
-```
-
-After the execution finishes, the `data/` directory should be like:
-
-```
-data
-├── backtest_orders.csv
-├── bin
-├── csv
-├── pickle
-├── pickle_dataframe
-└── training_order_split
-```
-
-## Run training
-
-Run:
-
-```
-python -m qlib.rl.contrib.train_onpolicy --config_path ./experiment_config/training/config.yml
-```
-
-After training, checkpoints will be stored under `checkpoints/`.
-
-## Run backtest
-
-```
-python -m qlib.rl.contrib.backtest --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/`.
-
-## Others
-The RL module is designed in a loosely-coupled way. Currently, RL examples are integrated with concrete business logic.
-But the core part of RL is much simpler than what you see.
-To demonstrate the simple core of RL, [a dedicated notebook](./simple_example.ipynb) for RL without business loss is created.
diff --git a/examples/rl/experiment_config/backtest/config.yml b/examples/rl/experiment_config/backtest/config.yml
deleted file mode 100644
index 418780c2cc..0000000000
--- a/examples/rl/experiment_config/backtest/config.yml
+++ /dev/null
@@ -1,57 +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: 
-  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
diff --git a/examples/rl/experiment_config/training/config.yml b/examples/rl/experiment_config/training/config.yml
deleted file mode 100644
index 7e50d3eee0..0000000000
--- a/examples/rl/experiment_config/training/config.yml
+++ /dev/null
@@ -1,59 +0,0 @@
-simulator:
-  time_per_step: 30
-  vol_limit: null
-env:
-  concurrency: 1
-  parallel_mode: dummy
-action_interpreter:
-  class: CategoricalActionInterpreter
-  kwargs:
-    values: 14
-    max_step: 8
-  module_path: qlib.rl.order_execution.interpreter
-state_interpreter:
-  class: FullHistoryStateInterpreter
-  kwargs:
-    data_dim: 6
-    data_ticks: 240
-    max_step: 8
-    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:
-    penalty: 100.0
-  module_path: qlib.rl.order_execution.reward
-data:
-  source:
-    order_dir: ./data/training_order_split
-    data_dir: ./data/pickle_dataframe/backtest
-    total_time: 240
-    default_start_time: 0
-    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
-  repeat_per_collect: 5
-  earlystop_patience: 2
-  episode_per_collect: 20
-  batch_size: 16
-  val_every_n_epoch: 1
-  checkpoint_path: ./checkpoints
-  checkpoint_every_n_iters: 1
diff --git a/examples/rl/scripts/collect_pickle_dataframe.py b/examples/rl/scripts/collect_pickle_dataframe.py
deleted file mode 100644
index 64dc94bdbc..0000000000
--- a/examples/rl/scripts/collect_pickle_dataframe.py
+++ /dev/null
@@ -1,21 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License.
-
-import os
-import pickle
-import pandas as pd
-from tqdm import tqdm
-
-os.makedirs(os.path.join("data", "pickle_dataframe"), exist_ok=True)
-
-for tag in ("backtest", "feature"):
-    df = pickle.load(open(os.path.join("data", "pickle", f"{tag}.pkl"), "rb"))
-    df = pd.concat(list(df.values())).reset_index()
-    df["date"] = df["datetime"].dt.date.astype("datetime64")
-    instruments = sorted(set(df["instrument"]))
-
-    os.makedirs(os.path.join("data", "pickle_dataframe", tag), exist_ok=True)
-    for instrument in tqdm(instruments):
-        cur = df[df["instrument"] == instrument].sort_values(by=["datetime"])
-        cur = cur.set_index(["instrument", "datetime", "date"])
-        pickle.dump(cur, open(os.path.join("data", "pickle_dataframe", tag, f"{instrument}.pkl"), "wb"))
diff --git a/examples/rl/scripts/data_pipeline.sh b/examples/rl/scripts/data_pipeline.sh
deleted file mode 100644
index c15b8fbe56..0000000000
--- a/examples/rl/scripts/data_pipeline.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-# Generate `bin` format data
-set -e
-python ../../scripts/dump_bin.py dump_all --csv_path ./data/csv --qlib_dir ./data/bin --include_fields open,close,high,low,vwap,volume --symbol_field_name symbol --date_field_name date --freq 1min
-
-# Generate pickle format data
-python scripts/gen_pickle_data.py -c scripts/pickle_data_config.yml
-if [ -e stat/ ]; then
-    rm -r stat/
-fi
-python scripts/collect_pickle_dataframe.py
-
-# Sample orders
-python scripts/gen_training_orders.py
-python scripts/gen_backtest_orders.py
diff --git a/examples/rl/scripts/gen_backtest_orders.py b/examples/rl/scripts/gen_backtest_orders.py
deleted file mode 100644
index 1857f64470..0000000000
--- a/examples/rl/scripts/gen_backtest_orders.py
+++ /dev/null
@@ -1,55 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License.
-
-import argparse
-import os
-import pandas as pd
-import numpy as np
-import pickle
-
-parser = argparse.ArgumentParser()
-parser.add_argument("--seed", type=int, default=20220926)
-parser.add_argument("--num_order", type=int, default=10)
-args = parser.parse_args()
-
-np.random.seed(args.seed)
-
-path = os.path.join("data", "pickle", "backtesttest.pkl")
-df = pickle.load(open(path, "rb")).reset_index()
-df["date"] = df["datetime"].dt.date.astype("datetime64")
-
-instruments = sorted(set(df["instrument"]))
-
-# TODO: The example is expected to be able to handle data containing missing values.
-# TODO: Currently, we just simply skip dates that contain missing data. We will add
-# TODO: this feature in the future.
-skip_dates = {}
-for instrument in instruments:
-    csv_df = pd.read_csv(os.path.join("data", "csv", f"{instrument}.csv"))
-    csv_df = csv_df[csv_df["close"].isna()]
-    dates = set([str(d).split(" ")[0] for d in csv_df["date"]])
-    skip_dates[instrument] = dates
-
-df_list = []
-for instrument in instruments:
-    print(instrument)
-
-    cur_df = df[df["instrument"] == instrument]
-
-    dates = sorted(set([str(d).split(" ")[0] for d in cur_df["date"]]))
-    dates = [date for date in dates if date not in skip_dates[instrument]]
-
-    n = args.num_order
-    df_list.append(
-        pd.DataFrame(
-            {
-                "date": sorted(np.random.choice(dates, size=n, replace=False)),
-                "instrument": [instrument] * n,
-                "amount": np.random.randint(low=3, high=11, size=n) * 100.0,
-                "order_type": np.random.randint(low=0, high=2, size=n),
-            }
-        ).set_index(["date", "instrument"]),
-    )
-
-total_df = pd.concat(df_list)
-total_df.to_csv("data/backtest_orders.csv")
diff --git a/examples/rl/scripts/gen_pickle_data.py b/examples/rl/scripts/gen_pickle_data.py
deleted file mode 100755
index f2dbbf1157..0000000000
--- a/examples/rl/scripts/gen_pickle_data.py
+++ /dev/null
@@ -1,43 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License.
-
-import yaml
-import argparse
-import os
-from copy import deepcopy
-
-from qlib.contrib.data.highfreq_provider import HighFreqProvider
-
-loader = yaml.FullLoader
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("-c", "--config", type=str, default="config.yml")
-    parser.add_argument("-d", "--dest", type=str, default=".")
-    parser.add_argument("-s", "--split", type=str, choices=["none", "date", "stock", "both"], default="stock")
-    args = parser.parse_args()
-
-    conf = yaml.load(open(args.config), Loader=loader)
-
-    for k, v in conf.items():
-        if isinstance(v, dict) and "path" in v:
-            v["path"] = os.path.join(args.dest, v["path"])
-    provider = HighFreqProvider(**conf)
-
-    # Gen dataframe
-    if "feature_conf" in conf:
-        feature = provider._gen_dataframe(deepcopy(provider.feature_conf))
-    if "backtest_conf" in conf:
-        backtest = provider._gen_dataframe(deepcopy(provider.backtest_conf))
-
-    provider.feature_conf["path"] = os.path.splitext(provider.feature_conf["path"])[0] + "/"
-    provider.backtest_conf["path"] = os.path.splitext(provider.backtest_conf["path"])[0] + "/"
-    # Split by date
-    if args.split == "date" or args.split == "both":
-        provider._gen_day_dataset(deepcopy(provider.feature_conf), "feature")
-        provider._gen_day_dataset(deepcopy(provider.backtest_conf), "backtest")
-
-    # Split by stock
-    if args.split == "stock" or args.split == "both":
-        provider._gen_stock_dataset(deepcopy(provider.feature_conf), "feature")
-        provider._gen_stock_dataset(deepcopy(provider.backtest_conf), "backtest")
diff --git a/examples/rl/scripts/gen_training_orders.py b/examples/rl/scripts/gen_training_orders.py
deleted file mode 100644
index 5dd1e96c67..0000000000
--- a/examples/rl/scripts/gen_training_orders.py
+++ /dev/null
@@ -1,39 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License.
-
-import argparse
-import os
-import pandas as pd
-import numpy as np
-import pickle
-
-parser = argparse.ArgumentParser()
-parser.add_argument("--seed", type=int, default=20220926)
-parser.add_argument("--stock", type=str, default="AAPL")
-parser.add_argument("--train_size", type=int, default=10)
-parser.add_argument("--valid_size", type=int, default=2)
-parser.add_argument("--test_size", type=int, default=2)
-args = parser.parse_args()
-
-np.random.seed(args.seed)
-
-os.makedirs(os.path.join("data", "training_order_split"), exist_ok=True)
-
-for group, n in zip(("train", "valid", "test"), (args.train_size, args.valid_size, args.test_size)):
-    path = os.path.join("data", "pickle", f"backtest{group}.pkl")
-    df = pickle.load(open(path, "rb")).reset_index()
-    df["date"] = df["datetime"].dt.date.astype("datetime64")
-
-    dates = sorted(set([str(d).split(" ")[0] for d in df["date"]]))
-
-    data_df = pd.DataFrame(
-        {
-            "date": sorted(np.random.choice(dates, size=n, replace=False)),
-            "instrument": [args.stock] * n,
-            "amount": np.random.randint(low=3, high=11, size=n) * 100.0,
-            "order_type": [0] * n,
-        }
-    ).set_index(["date", "instrument"])
-
-    os.makedirs(os.path.join("data", "training_order_split", group), exist_ok=True)
-    pickle.dump(data_df, open(os.path.join("data", "training_order_split", group, f"{args.stock}.pkl"), "wb"))
diff --git a/examples/rl/scripts/pickle_data_config.yml b/examples/rl/scripts/pickle_data_config.yml
deleted file mode 100755
index 7813f7d386..0000000000
--- a/examples/rl/scripts/pickle_data_config.yml
+++ /dev/null
@@ -1,57 +0,0 @@
-# start & end time for training/validation/test datasets
-start_time: !!str &start 2020-01-01
-end_time: !!str &end 2020-07-31
-train_end_time: !!str &tend 2020-03-31
-valid_start_time: !!str &vstart 2020-04-01
-valid_end_time: !!str &vend 2020-05-31
-test_start_time: !!str &tstart 2020-06-01
-# the instrument set
-instruments: &ins all
-# qlib related configuration
-qlib_conf:
-    provider_uri: ./data/bin # path to generated qlib bin
-    redis_port: 233
-feature_conf:
-    path: ./data/pickle/feature.pkl # output path of feature
-    class: DatasetH
-    module_path: qlib.data.dataset
-    kwargs:
-        handler:
-            class: HighFreqGeneralHandler
-            module_path: qlib.contrib.data.highfreq_handler
-            kwargs:
-                start_time: *start
-                end_time: *end
-                fit_start_time: *start
-                fit_end_time: *tend
-                instruments: *ins
-                day_length: 240 # how many minutes in one trading day
-                infer_processors:
-                - class: HighFreqNorm
-                  module_path: qlib.contrib.data.highfreq_processor
-                  kwargs:
-                    feature_save_dir: ./stat/  #  output path of statistics of features (for feature normalization)
-                    norm_groups: 
-                        price: 10
-                        volume: 2
-        segments:
-            train: !!python/tuple [*start, *tend]
-            valid: !!python/tuple [*vstart, *vend]
-            test: !!python/tuple [*tstart, *end]
-backtest_conf:
-    path: ./data/pickle/backtest.pkl # output path of backtest
-    class: DatasetH
-    module_path: qlib.data.dataset
-    kwargs:
-        handler:
-            class: HighFreqGeneralBacktestHandler
-            module_path: qlib.contrib.data.highfreq_handler
-            kwargs:
-                start_time: *start
-                end_time: *end
-                instruments: *ins
-                day_length: 240
-        segments:
-            train: !!python/tuple [*start, *tend]
-            valid: !!python/tuple [*vstart, *vend]
-            test: !!python/tuple [*tstart, *end]