Refine Qlib RL data format (#1480)

* 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>

examples/rl_order_execution/README.md

@@ -14,9 +14,10 @@ python -m qlib.run.get_data qlib_data qlib_data --target_dir ./data/bin --region
 
 To run codes in this example, we need data in pickle format. To achieve this, run following commands (might need a few minutes to finish):
 
+[//]: # (TODO: Instead of dumping dataframe with different format (like `_gen_dataset` and `_gen_day_dataset` in `qlib/contrib/data/highfreq_provider.py`), we encourage to implement different subclass of `Dataset` and `DataHandler`. This will keep the workflow cleaner and interfaces more consistent, and move all the complexity to the subclass.)
+
 ```
 python scripts/gen_pickle_data.py -c scripts/pickle_data_config.yml
-python scripts/collect_pickle_dataframe.py
 python scripts/gen_training_orders.py
 python scripts/merge_orders.py
 ```
@@ -27,8 +28,7 @@ When finished, the structure under `data/` should be:
 data
 ├── bin
 ├── orders
-├── pickle
-└── pickle_dataframe
+└── pickle
 ```
 
 ## Training