yuriak / rlquant Goto Github PK

Getting this error when running the agent.
Anyone was successful with this code and can cooperate?

Hello,
When I run PairsTradingTutorial.ipynb to trade, the train_reward is always nan, as follows:

train_reward: nan
train_reward: nan
train_reward: nan
train_reward: nan
...

I couldn't find what's wrong with the code,could you please help me?
By the way, I wonder the version of packages we used is different, What versions of packages are you using now ?

Thank you very much.

all the input array dimensions except for the concatenation axis must match exactly
in:
def _get_normalized_state(self):
...
return np.concatenate((state, self.current_weight[:-1][:, None]), axis=1)

Any idea?

When running the agent.
Anyone was successful in running this code and can cooperate?

Hello,
Can I still use the PairsTradingTutorial.ipynb to trade some other dataset? I have a dataset of a forex pair which contains O H L C prices and Volume (I can add also some indicators), and I wonder if the example that you're giving in thtat jupyter notebook will work for this dataset.

Thank you!

Hi,

Running EnvtestStock_RPG.ipynb I get the following error:
`---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
in
14 state=next_state
15 if env.pointer%64==0:
---> 16 agent.train()
17 pv,pp,pw=env.get_summary()
18 total_pv=pv.sum(axis=1)

in train(self)
73 def train(self):
74 self.optimizer.zero_grad()
---> 75 s = torch.stack(self.s_buffer).t()
76 s_next = torch.stack(self.s_next_buffer).t()
77 r = torch.stack(self.r_buffer).t()

RuntimeError: t() expects a 2D tensor, but self is 3D`

In particular, self.s_buffer is a list of 54 tensors, each of size: torch.Size([6, 36])

Do you know what might be causing it?

Thank you in advance

EDIT: my torch version is 1.0.1

there is no data folder and pkl files supplied. From where these can be downloaded?

This is great, it just needs a description of the data collection and processing.