error when running model.fit

[pongponglau]

Thank you so much for this great project.

When i try to run ddqn_rl_trader.py on windows (my computer has no GPU, so i use LSTM instead of CuDNNLSTM), i get the following errors:

2019-01-17 17:06:16.101245: I T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary start episode ... XBTUSD_5m_70000_train.csv at 0 Traceback (most recent call last): File "ddqn_rl_trader.py", line 81, in main() File "ddqn_rl_trader.py", line 65, in main dqn.fit(env, nb_steps=5500, nb_max_episode_steps=10000, visualize=False, verbose=0) File "C:\Python36\lib\site-packages\rl\core.py", line 182, in fit if not np.isreal(value): ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

May i ask what change i can make to this problem?

Thanks a lot

[Jack30e]

I'm having the same error... has anyone a solution?

[ghost]

@miroblog I am having the same issue. Do you have an idea?

(Pdb) dqn.fit(env, nb_steps=5500, nb_max_episode_steps=10000, visualize=False, verbose=2) Training for 5500 steps ... start episode ... XBTUSD_5m_70000_train.csv at 0 *** ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or

ENV_NAME = 'OHLCV-v0'
TIME_STEP = 30
PATH_TRAIN = "./data/train/"
PATH_TEST = "./data/test/"
env = OhlcvEnv(TIME_STEP, path=PATH_TRAIN)
env_test = OhlcvEnv(TIME_STEP, path=PATH_TEST)

def create_model(shape, nb_actions):
    model = Sequential()
    model.add(LSTM(64, input_shape=shape, return_sequences=True))
    model.add(LSTM(64))
    model.add(Dense(32))
    model.add(Activation('relu'))
    model.add(Dense(nb_actions, activation='linear'))
    return model
np.random.seed(123)
env.seed(123)

# create_model
nb_actions = env.action_space.n
model = create_model(shape=env.shape, nb_actions=nb_actions)
print(model.summary())

# create memory
memory = SequentialMemory(limit=50000, window_length=TIME_STEP)

# create policy
policy = EpsGreedyQPolicy()# policy = BoltzmannQPolicy()

# create agent
# you can specify the dueling_type to one of {'avg','max','naive'}

dqn = DQNAgent(model=model, nb_actions=nb_actions, memory=memory, nb_steps_warmup=200,  enable_dueling_network=True, dueling_type='avg', target_model_update=1e-2, policy=policy, processor=NormalizerProcessor())
dqn.compile(Adam(lr=1e-3), metrics=['mae'])

while True:
    # train
    pdb.set_trace()
    dqn.fit(env, nb_steps=5500, nb_max_episode_steps=10000, visualize=False, verbose=2)

[GenesisGupta]

pls change the file of C:\Python36\lib\site-packages\rl\core.py with the core.py file given here : deep_rl_trader/modified_keras_rl_core/

let me know in case you are facing any problems.

if somebody is wishing to collaborate on this , i am willing to collaborate

[GenesisGupta]

Hi,

I am not the owner of this project , but looking at creating a bot that can trade on itself.

I also trade crypto currencies using systematic trading models.

Regards, Nitin Gupta 9731423808

On Mon, Mar 25, 2019 at 4:48 PM Caner Çakmak notifications@github.com wrote:

@GenesisGupta https://github.com/GenesisGupta it works now, thank you. I am willing to colloborate in creating a binance trading bot with backtest and live trading that continuously trains on Open AI Gym. Could not see your contributions, are you the owner of the project?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/miroblog/deep_rl_trader/issues/2#issuecomment-476153583, or mute the thread https://github.com/notifications/unsubscribe-auth/Aam05pkCQ8XIkOtbXwN8AbBPiY0YADsLks5vaLCZgaJpZM4aEw7l .

[raghavb]

Hey, how did you guys install all the requirements? There are so many versions of dependencies that are not available. Any help would be highly appreciated. Thanks!

[ghost]

install in conda env, try installing the ones that don't work by removing the version tag

[netvienna]

pls change the file of C:\Python36\lib\site-packages\rl\core.py with the core.py file given here : deep_rl_trader/modified_keras_rl_core/

let me know in case you are facing any problems.

if somebody is wishing to collaborate on this , i am willing to collaborate

thx. On linux got to your environment folder /home/username.../anaconda3/envs/bt4ker/lib/python3.6/site-packages/rl/ and replace it. Then it works. Thx for the hint.