Hi! Is there any example or usage direction for cryptocurrency trading?

[kangyining]

As title, thanks in advance!

[Athe-kunal]

https://github.com/AI4Finance-Foundation/FinRL-Meta/blob/master/Demo_MultiCrypto_Trading.ipynb

[kangyining]

Thank you!

[Burntt]

Corresponding YT video (also produced by us)

https://www.youtube.com/watch?v=aJAbgJf6AFM&t=698s

[kangyining]

Thanks!

[kangyining]

Thanks for all the replies!

However, this notebook doesn't seem to work on my colab. It seems these two lines don't work:

!pip install git+https://github.com/AI4Finance-LLC/ElegantRL.git
!pip install git+https://github.com/AI4Finance-LLC/FinRL-Library.git

leading to failure here:

from drl_agents.elegantrl_models import DRLAgent as DRLAgent_erl
from drl_agents.rllib_models import DRLAgent as DRLAgent_rllib
from drl_agents.stablebaselines3_models import DRLAgent as DRLAgent_sb3
from finrl_meta.data_processor import DataProcessor

where it says:
ModuleNotFoundError: No module named 'elegantrl'

Is there any other way to make this work as a library instead of cloning these two repos and change corresponding imports?

[Burntt]

Hey I struggled with this for a bit as well and the new functions are in a subfolder called train on ElegantRL (follow this link and see the structure):

https://github.com/AI4Finance-Foundation/ElegantRL/tree/master/elegantrl

First clone ElegantRL in your FinRL-Meta workspace:

import sys
%cd /FinRL-Meta/
!git clone https://github.com/AI4Finance-LLC/ElegantRL.
sys.path.append("/FinRL-Meta/ElegantRL")
import elegantrl

They used to be in a folder above so what you have to do in the Python file:

elegantrl_models.py

Change the following lines:

from elegantrl.agent import AgentDDPG
from elegantrl.agentimport AgentPPO
from elegantrl.agent import AgentSAC
from elegantrl.agent import AgentTD3
from elegantrl.run import train_and_evaluate, init_agent
from elegantrl.config import Arguments

into:

from elegantrl.agents import AgentDDPG
from elegantrl.agents import AgentPPO
from elegantrl.agents import AgentSAC
from elegantrl.agents import AgentTD3
from elegantrl.train.run import train_and_evaluate, init_agent
from elegantrl.train.config import Arguments

Ok, now we get a new error, which indicates that 'SharePPO' is not present in the 'elegantrl.agents.net', which is true. Therefore, I removed those imports which do not exist.

ImportError: cannot import name 'SharePPO' from 'elegantrl.agents.net' (/FinRL-Meta/ElegantRL/elegantrl/agents/net.py)
ImportError: cannot import name 'ShareSPG' from 'elegantrl.agents.net' (/FinRL-Meta/ElegantRL/elegantrl/agents/net.py)
ImportError: cannot import name 'CriticMultiple' from 'elegantrl.agents.net' (/FinRL-Meta/ElegantRL/elegantrl/agents/net.py)

Finally, for some reason two packages are missing after that, so to the installation cell I added:

!pip install baostock
!pip install quandl

And then it worked! Should merge this into a pull request soon. Thank you

[Burntt]

This is handled in the video! Explains all 👍🏻

There have been a few updates to ElegantRL and we need to work on that, we will get there soon!

[kangyining]

Sure, let me check that. Thanks a lot!

[kangyining]

Still some errors:
Code:

train(start_date=TRAIN_START_DATE, 
      end_date=TRAIN_END_DATE,
      ticker_list=TICKER_LIST, 
      data_source='binance',
      time_interval='5m', 
      technical_indicator_list=TECHNICAL_INDICATORS_LIST,
      drl_lib='elegantrl', 
      env=env, 
      model_name='ppo', 
      current_working_dir='./test_ppo',
      erl_params=ERL_PARAMS,
      break_step=5e4,
      if_vix=False
      )

Output:

Not support for {self.data_source}
{self.data_source} successfully connected
Using cached file ./cache/BTCUSDT_ETHUSDT_ADAUSDT_BNBUSDT_XRPUSDT_SOLUSDT_DOTUSDT_DOGEUSDT_AVAXUSDT_UNIUSDT_binance_2021-09-01_2021-09-20_5m.pickle
tech_indicator_list:  ['macd', 'rsi', 'cci', 'dx']
indicator:  macd
indicator:  rsi
indicator:  cci
indicator:  dx
Succesfully add technical indicators
Successfully transformed into array
| Arguments Remove cwd: ./test_ppo

Errors:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
[<ipython-input-40-0e8fc459cfcb>](https://localhost:8080/#) in <module>()
     11       erl_params=ERL_PARAMS,
     12       break_step=5e4,
---> 13       if_vix=False
     14       )

3 frames
[<ipython-input-34-ea6d6205e665>](https://localhost:8080/#) in train(start_date, end_date, ticker_list, data_source, time_interval, technical_indicator_list, drl_lib, env, model_name, if_vix, **kwargs)
     34         trained_model = agent.train_model(model=model, 
     35                                           cwd=current_working_dir,
---> 36                                           total_timesteps=break_step)
     37 
     38     elif drl_lib == 'rllib':

[/FinRL-Meta/drl_agents/elegantrl_models.py](https://localhost:8080/#) in train_model(self, model, cwd, total_timesteps)
     80         model.cwd = cwd
     81         model.break_step = total_timesteps
---> 82         train_and_evaluate(args=model)
     83 
     84     @staticmethod

[/FinRL-Meta/ElegantRL/elegantrl/train/run.py](https://localhost:8080/#) in train_and_evaluate(args)
     20     env = build_env(args.env, args.env_func, args.env_args)
     21 
---> 22     agent = init_agent(args, gpu_id, env)
     23     buffer = init_buffer(args, gpu_id)
     24     evaluator = init_evaluator(args, gpu_id)

[/FinRL-Meta/ElegantRL/elegantrl/train/run.py](https://localhost:8080/#) in init_agent(args, gpu_id, env)
     62 
     63 def init_agent(args, gpu_id, env=None):
---> 64     agent = args.agent(args.net_dim, args.state_dim, args.action_dim, gpu_id=gpu_id, args=args)
     65     agent.save_or_load_agent(args.cwd, if_save=False)
     66 

TypeError: 'module' object is not callable

[kangyining]

Hi Burntt,

I've tried your new commit, and it seems the 'module' object is not callable preserves.
Any idea on this one?

Thanks a lot!

[kangyining]

FYI, I'm running this on Google Colab. I saw your output on the .ipynb, would you mind telling me what kind of running environment you used for this notebook?