I'm currently working on a Chess AI.
The idea behind this project is to create a neural network that learns how to evaluate a board state and then traverse the next moves using Monte Carlo tree search to find the "best" move to play (evaluated by the NN).
Code on GitHub
TL;DR
The NN gets stuck predicting the average evaluation of the dataset and is thereby not learning to predict the evaluation of the board state.
Implementation
Dataset
The dataset is a collection of chess games. The games are fetched from the official lichess database.
Only games which have a evaluation score (which the NN is supposed to learn) are included.
This reduces the size of the dataset to about 11% of the original.
Data representation
Each move is a datapoint to train the network on.
The input for the NN are 12 arrays of size 8x8 (so called Bitboards), one for each of the 6x2 different pieces and colors.
The move evaluation is normalized to the range [-1, 1] using a scaled tanh function.
Since many evaluations are very close to 0 and -1/1, a percentage of these are dropped aswell, to reduce the variation in the dataset.
Without dropping some of the moves with evaluation close to 0 or -1/1 the dataset would look like this:
With dropping some, the dataset looks like this and is a lot less focused at one point:
The output of the NN is a single scalar value between -1 and 1, representing the evaluation of the board state. -1 meaning the board is heavily favored for the black player, 1 meaning the board is heavily favored for the white player.
def create_training_data(dataset: DataFrame) -> Tuple[np.ndarray, np.ndarray]:
def drop(indices, fract):
drop_index = np.random.choice(
indices,
size=int(len(indices) * fract),
replace=False)
dataset.drop(drop_index, inplace=True)
drop(dataset[abs(dataset[12] / 10.) > 30].index, fract=0.80)
drop(dataset[abs(dataset[12] / 10.) < 0.1].index, fract=0.90)
drop(dataset[abs(dataset[12] / 10.) < 0.15].index, fract=0.10)
# the first 12 entries are the bitboards for the pieces
y = dataset[12].values
X = dataset.drop(12, axis=1)
# move into range of -1 to 1
y = y.astype(np.float32)
y = np.tanh(y / 10.)
return X, y
The neural network
The neural network is implemented using Keras.
The CNN is used to extract features from the board, then passed to a dense network to reduce to an evaluation. This is based on the NN AlphaGo Zero has used in its implementation.
The CNN is implemented as follows:
model = Sequential()
model.add(Conv2D(256, (3, 3), activation='relu', padding='same', input_shape=(12, 8, 8, 1)))
for _ in range(10):
model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(BatchNormalization())
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(units=64, activation='relu'))
# model.add(Rescaling(scale=1 / 10., offset=0)) required? Data gets scaled in create_training_data, does the Network learn that/does doing that explicitly help?
model.add(Dense(units=1, activation='tanh'))
model.compile(
loss='mean_squared_error',
optimizer=Adam(learning_rate=0.01),
# metrics=['accuracy', 'mse'] # do these influence training at all?
)
Training
The training is done using Keras.
Multiple sets of 50k-500k moves are used to train the network.
The network is trained for 20 epochs on each move set with a batchsize of 64 and 10% of moves are used for validation.
Afterwards the learning rate is adjusted by 0.001 / (index + 1).
for i, chunk in enumerate(pd.read_csv("../dataset/nm_games.csv", header=None, chunksize=100000)):
X, y = create_training_data(chunk)
model.fit(
X,
y,
epochs=20,
batch_size=64,
validation_split=0.1
)
model.optimizer.learning_rate = 0.001 / (i + 1)
Issues
The NN currently does not learn anything. It converges within a few epochs to a average evaluation of the dataset and does not predict anything depending on the board state.
Example after 20 epochs:
Dataset Evaluation
NN Evaluation
Difference
-0.10164772719144821
0.03077016
0.13241789
0.6967725157737732
0.03180310
0.66496944
-0.3644430935382843
0.03119821
0.39564130
0.5291759967803955
0.03258476
0.49659124
-0.25989893078804016
0.03316733
0.29306626
The NN Evaluation is stuck at 0.03, which is the approximate average evaluation of the dataset.
It is also stuck there, not continuing to improve.
What I tried
Increased and decreased NN size
Added up to 20 extra Conv2D layers since google did that in their implementation aswell
Removed all 10 extra Conv2D layers since I read that many NN are too complex for the dataset
Trained for days at a time
Since the NN is stuck at 0.03, and also doesn't move from there, that was wasted.
Dense NN instead of CNN
Did not eliminate the point where the NN gets stuck, but trains faster (aka. gets stuck faster :) )
model = Sequential()
model.add(Dense(2048, input_shape=(12 * 8 * 8,), activation='relu'))
model.add(Dense(2048, activation='relu'))
model.add(Dense(2048, activation='relu'))
model.add(Dense(1, activation='tanh'))
model.compile(
loss='mean_squared_error',
optimizer=Adam(learning_rate=0.001),
# metrics=['accuracy', 'mse']
)
Sigmoid activation instead of tanh
Moves evaluation from a range of -1 to 1 to a range of 0 to 1 but otherwise did not change anything about getting stuck.
Epochs, batchsize and chunksize increased and decreased
All of these changes did not significantly change the NN evaluation.
Learning Rate addaption
Larger learning rates (0.1) made the NN unstable, each time training, converging to either -1, 1 or 0.
Smaller learning rates (0.0001) made the NN converge slower, but still stuck at 0.03.
Code on GitHub
Question
What to do? Is there something I'm missing or is there an error?
my two suggestions:
use the full dataset and score each position based on the fact if that player won the game or not. i don't know this dataset and there might be something with the evaluations by others ( or are they verified?) even if you are sure about the validity of it i would test this as it can provide some more information on what the problem might be
Check your data representation. probably you already did this a couple of times but i can tell you from experience it is easy to introduce one and to overlook them. adding a test might help you in the long run. some of my problems:
indication of current player colour? not sure if you have a player colour plane or you switch current player pieces?
incorrect translation from 1d to 3d or vice-versa. (should not prevent you from training but saves you a lot of time if you want to port to a different device)
I trained a go game engine and do not know what representation is used for chess, it took me some time to figure out a good representation for checkers.
not a solution but i found that cyclic learning rates worked great for my go-engine might be something to look at when the rest works
Related
I created a randomly generated(using numpy, between range 30 and 60) Data of about 12000 points (to
generate an artificial time-series data for more than a year in Time).
Now I am trying to fit that data points in an LSTM model and forecast
based upon that.
The LSTM model i applied,(here data is a single series so n_features = 1, and steps-in and out are for sequence-generation function for time-series, i took both equal to 5. Also the for the activation functions i tried all with both relu, both tanh and 1st tanh & 2nd relu (as shown here))
X, y = split_sequences(data, n_steps_in, n_steps_out)
n_features = X.shape[2]
model = Sequential()
model.add(LSTM(200, activation='tanh', input_shape=(n_steps_in,
n_features)))
model.add(RepeatVector(n_steps_out))
model.add(LSTM(200, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(n_features)))
opt = keras.optimizers.Adam(learning_rate=0.05)
model.compile(optimizer=opt, loss='mse')
model.fit(X, y, epochs= n, batch_size=10, verbose=1,
workers=4, use_multiprocessing = True, initial_epoch = 0)
I also tried smoothening of the data-points as they are randomly
distributed (in the predefined boundaries).
and then applied the model on the smoothed data, but still i am getting similar results.
for e.g., In this image showing both the smoothed-training data and the forecasted-prediction from the model
plt.plot(Training_data, 'g')
plt.plot(Pred_Forecasts,'r')
Every time the models are giving straight lines in prediction.
and which is obvious since it is a set of random numbers so model tends to get to a mean value between the upper and lower limits of the data, but still is there any way to generate a somewhat real looking model.
P.S-1 - I have also tried applying different models like prophet, sarima, arima.
But i think i need to find a way to increase the Variance of the prediction, which i am unable to find.
PS-2 - Sorry for the long question i am new to deep-learning so i tried to explain more.
I working on using LSTMs and GRUs to make time series predictions. For the most part the predictions are pretty good.
However, there seems to be a wiggle (or initial up-then-down) before the prediction settles out similar to the left side of this figure from another question.
In my case, it is also causing a slight offset. Does anyone have any idea why this might be the case? Below are the shapes of the training and test sets, as well as the current network structure. I've tried reducing the sequence lengths from 60 timesteps, switching between LSTMs and GRUs, and also having the inputs and outputs overlap slightly, all to no avail. Adding dropout does not seem to help either. The wiggles will not disappear!
My sequence lengths are 60 inputs and 60 outputs, currently.
Xtrain: (920, 60, 2)
Ytrain: (920, 60, 2)
Xtest: (920, 60, 2)
Ytest: (920, 60, 2)
def define_model():
model = Sequential()
model.add(LSTM(64, return_sequences=True, input_shape=(None, 2)))
model.add(LSTM(64, return_sequences=True))
model.add(LSTM(64, return_sequences=True))
model.add(TimeDistributed(Dense(2)))
model.add(Activation('linear'))
model.summary()
return model
As they are "recurrent" networks, they have a direction. There is no memory at all for the first step, and the initial steps have a few memory.
Memory is only built after a few steps, only then it's possible to understand how a sequence is evolving.
The usual solution to this is to use a Bidirectional wrapper, so you have x units working from start to end and another x units working from end to start.
model.add(Bidirectional(LSTM(32, return_sequences = True), input_shape=...))
As for the offset, this is probably something with the data preprocessing.
I'm trying to train a neural network to predict the ratings for players in FIFA 18 by easports (ratings are between 64-99). I'm using their players database (https://easports.com/fifa/ultimate-team/api/fut/item?page=1) and I've processed the data into training_x, testing_x, training_y, testing_y. Each of the training samples is a numpy array containing 7 values...the first 6 are the different stats of the player (shooting, passing, dribbling, etc) and the last value is the position of the player (which I mapped between 1-8, depending on the position), and each of the testing values is a single integer between 64-99, representing the rating of that player.
I've tried many different hyperparameters, including changing the activation functions to tanh and relu, and I've tried adding a batch normalization layer after the first dense layer (I thought that it might be useful since one of my features is very small and the other features are between 50-99), I've played around with the SGD optimizer (changed the learning rate, momentum, even tried changing the optimizer to Adam), tried different loss functions, added/removed dropout layers, and tried different regularizers for the weights of the model.
model = Sequential()
model.add(Dense(64, input_shape=(7,),
kernel_regularizer=regularizers.l2(0.01)))
//batch normalization?
model.add(Activation('sigmoid'))
model.add(Dense(64, kernel_regularizer=regularizers.l2(0.01),
activation='sigmoid'))
model.add(Dropout(0.3))
model.add(Dense(32, kernel_regularizer=regularizers.l2(0.01),
activation='sigmoid'))
model.add(Dense(1, activation='linear'))
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_absolute_error', metrics=['accuracy'],
optimizer=sgd)
model.fit(training_x, training_y, epochs=50, batch_size=128, shuffle=True)
When I train the model, the loss is always nan and the accuracy is always 0, even though I've tried adjusting a lot of different parameters. However, if I remove the last feature from my data, the position of the players, and update the input shape of the first dense layer, the model actually "trains" and ends up with around 6% accuracy no matter what parameters I change. In that case, I've found that the model only predicts 79 to be the player's rating. What am I doing inherently wrong?
You can try the following steps :
Use mean squared error loss function.
Use Adam which will help you converge faster with low learning rate like 0.0001 or 0.001. Otherwise, try using the RMSprop optimizer.
Use the default regularizers. That is none actually.
Since this is a regression task, use activation function like ReLU in all the layers except the output layer ( including the input layer ). Use linear activation in output layer.
As mentioned in the comments by #pooyan , normalize the features. See here. Even try standardizing the features. Use whichever suites the best.
I am trying to predict the hygrothermal response of a wall, given the interior and exterior climate. Based on literature research, I believe this should be possible with RNN but I have not been able to get good accuracy.
The dataset has 12 input features (time-series of exterior and interior climate data) and 10 output features (time-series of hygrothermal response), both containing hourly values for 10 years. This data was created with hygrothermal simulation software, there is no missing data.
Dataset features:
Dataset targets:
Unlike most time-series prediction problems, I want to predict the response for the full length of the input features time-series at each time-step, rather than the subsequent values of a time-series (eg financial time-series prediction). I have not been able to find similar prediction problems (in similar or other fields), so if you know of one, references are very welcome.
I think this should be possible with RNN, so I am currently using LSTM from Keras. Before training, I preprocess my data the following way:
Discard first year of data, as the first time steps of the hygrothermal response of the wall is influenced by the initial temperature and relative humidity.
Split into training and testing set. Training set contains the first 8 years of data, the test set contains the remaining 2 years.
Normalise training set (zero mean, unit variance) using StandardScaler from Sklearn. Normalise test set analogously using mean an variance from training set.
This results in: X_train.shape = (1, 61320, 12), y_train.shape = (1, 61320, 10), X_test.shape = (1, 17520, 12), y_test.shape = (1, 17520, 10)
As these are long time-series, I use stateful LSTM and cut the time-series as explained here, using the stateful_cut() function. I only have 1 sample, so batch_size is 1. For T_after_cut I have tried 24 and 120 (24*5); 24 appears to give better results. This results in X_train.shape = (2555, 24, 12), y_train.shape = (2555, 24, 10), X_test.shape = (730, 24, 12), y_test.shape = (730, 24, 10).
Next, I build and train the LSTM model as follows:
model = Sequential()
model.add(LSTM(128,
batch_input_shape=(batch_size,T_after_cut,features),
return_sequences=True,
stateful=True,
))
model.addTimeDistributed(Dense(targets)))
model.compile(loss='mean_squared_error', optimizer=Adam())
model.fit(X_train, y_train, epochs=100, batch_size=batch=batch_size, verbose=2, shuffle=False)
Unfortunately, I don't get accurate prediction results; not even for the training set, thus the model has high bias.
The prediction results of the LSTM model for all targets
How can I improve my model? I have already tried the following:
Not discarding the first year of the dataset -> no significant difference
Differentiating the input features time-series (subtract previous value from current value) -> slightly worse results
Up to four stacked LSTM layers, all with the same hyperparameters -> no significant difference in results but longer training time
Dropout layer after LSTM layer (though this is usually used to reduce variance and my model has high bias) -> slightly better results, but difference might not be statistically significant
Am I doing something wrong with the stateful LSTM? Do I need to try different RNN models? Should I preprocess the data differently?
Furthermore, training is very slow: about 4 hours for the model above. Hence I am reluctant to do an extensive hyperparameter gridsearch...
In the end, I managed to solve this the following way:
Using more samples to train instead of only 1 (I used 18 samples to train and 6 to test)
Keep the first year of data, as the output time-series for all samples have the same 'starting point' and the model needs this information to learn
Standardise both input and output features (zero mean, unit variance). I found this improved prediction accuracy and training speed
Use stateful LSTM as described here, but add reset states after epoch (see below for code). I used batch_size = 6 and T_after_cut = 1460. If T_after_cut is longer, training is slower; if T_after_cut is shorter, accuracy decreases slightly. If more samples are available, I think using a larger batch_size will be faster.
use CuDNNLSTM instead of LSTM, this speed up the training time x4!
I found that more units resulted in higher accuracy and faster convergence (shorter training time). Also I found that the GRU is as accurate as the LSTM tough converged faster for the same number of units.
Monitor validation loss during training and use early stopping
The LSTM model is build and trained as follows:
def define_reset_states_batch(nb_cuts):
class ResetStatesCallback(Callback):
def __init__(self):
self.counter = 0
def on_batch_begin(self, batch, logs={}):
# reset states when nb_cuts batches are completed
if self.counter % nb_cuts == 0:
self.model.reset_states()
self.counter += 1
def on_epoch_end(self, epoch, logs={}):
# reset states after each epoch
self.model.reset_states()
return(ResetStatesCallback)
model = Sequential()
model.add(layers.CuDNNLSTM(256, batch_input_shape=(batch_size,T_after_cut ,features),
return_sequences=True,
stateful=True))
model.add(layers.TimeDistributed(layers.Dense(targets, activation='linear')))
optimizer = RMSprop(lr=0.002)
model.compile(loss='mean_squared_error', optimizer=optimizer)
earlyStopping = EarlyStopping(monitor='val_loss', min_delta=0.005, patience=15, verbose=1, mode='auto')
ResetStatesCallback = define_reset_states_batch(nb_cuts)
model.fit(X_dev, y_dev, epochs=n_epochs, batch_size=n_batch, verbose=1, shuffle=False, validation_data=(X_eval,y_eval), callbacks=[ResetStatesCallback(), earlyStopping])
This gave me very statisfying accuracy (R2 over 0.98):
This figure shows the temperature (left) and relative humidity (right) in the wall over 2 years (data not used in training), prediction in red and true output in black. The residuals show that the error is very small and that the LSTM learns to capture the long-term dependencies to predict the relative humidity.
I am attempting to train an ANN on time series data in Keras. I have three vectors of data that are broken into scrolling window sequences (i.e. for vector l).
np.array([l[i:i+window_size] for i in range( len(l) - window_size)])
The target vector is similarly windowed so the neural net output is a prediction of the target vector for the next window_size number of time steps. All the data is normalized with a min-max scaler. It is fed into the neural network as a shape=(nb_samples, window_size, 3). Here is a plot of the 3 input vectors.
The only output I've managed to muster from the ANN is the following plot. Target vector in blue, predictions in red (plot is zoomed in to make the prediction pattern legible). Prediction vectors are plotted at window_size intervals so each one of the repeated patterns is one prediction from the net.
I've tried many different model architectures, number of epochs, activation functions, short and fat networks, skinny, tall. This is my current one (it's a little out there).
Conv1D(64,4, input_shape=(None,3)) ->
Conv1d(32,4) ->
Dropout(24) ->
LSTM(32) ->
Dense(window_size)
But nothing I try will affect the neural net from outputting this repeated pattern. I must be misunderstanding something about time-series or LSTMs in Keras. But I'm very lost at this point so any help is greatly appreciated. I've attached the full code at this repository.
https://github.com/jaybutera/dat-toy
I played with your code a little and I think I have a few suggestions for getting you on the right track. The code doesn't seem to match your graphs exactly, but I assume you've tweaked it a bit since then. Anyway, there are two main problems:
The biggest problem is in your data preparation step. You basically have the data shapes backwards, in that you have a single timestep of input for X and a timeseries for Y. Your input shape is (18830, 1, 8), when what you really want is (18830, 30, 8) so that the full 30 timesteps are fed into the LSTM. Otherwise the LSTM is only operating on one timestep and isn't really useful. To fix this, I changed the line in common.py from
X = X.reshape(X.shape[0], 1, X.shape[1])
to
X = windowfy(X, winsize)
Similarly, the output data should probably be only 1 value, from what I've gathered of your goals from the plotting function. There are certainly some situations where you want to predict a whole timeseries, but I don't know if that's what you want in this case. I changed Y_train to use fuels instead of fuels_w so that it only had to predict one step of the timeseries.
Training for 100 epochs might be way too much for this simple network architecture. In some cases when I ran it, it looked like there was some overfitting going on. Observing the decrease of loss in the network, it seems like maybe only 3-4 epochs are needed.
Here is the graph of predictions after 3 training epochs with the adjustments I mentioned. It's not a great prediction, but it looks like it's on the right track now at least. Good luck to you!
EDIT: Example predicting multiple output timesteps:
from sklearn import datasets, preprocessing
import numpy as np
from scipy import stats
from keras import models, layers
INPUT_WINDOW = 10
OUTPUT_WINDOW = 5 # Predict 5 steps of the output variable.
# Randomly generate some regression data (not true sequential data; samples are independent).
np.random.seed(11798)
X, y = datasets.make_regression(n_samples=1000, n_features=4, noise=.1)
# Rescale 0-1 and convert into windowed sequences.
X = preprocessing.MinMaxScaler().fit_transform(X)
y = preprocessing.MinMaxScaler().fit_transform(y.reshape(-1, 1))
X = np.array([X[i:i + INPUT_WINDOW] for i in range(len(X) - INPUT_WINDOW)])
y = np.array([y[i:i + OUTPUT_WINDOW] for i in range(INPUT_WINDOW - OUTPUT_WINDOW,
len(y) - OUTPUT_WINDOW)])
print(np.shape(X)) # (990, 10, 4) - Ten timesteps of four features
print(np.shape(y)) # (990, 5, 1) - Five timesteps of one features
# Construct a simple model predicting output sequences.
m = models.Sequential()
m.add(layers.LSTM(20, activation='relu', return_sequences=True, input_shape=(INPUT_WINDOW, 4)))
m.add(layers.LSTM(20, activation='relu'))
m.add(layers.RepeatVector(OUTPUT_WINDOW))
m.add(layers.LSTM(20, activation='relu', return_sequences=True))
m.add(layers.wrappers.TimeDistributed(layers.Dense(1, activation='sigmoid')))
print(m.summary())
m.compile(optimizer='adam', loss='mse')
m.fit(X[:800], y[:800], batch_size=10, epochs=60) # Train on first 800 sequences.
preds = m.predict(X[800:], batch_size=10) # Predict the remaining sequences.
print('Prediction:\n' + str(preds[0]))
print('Actual:\n' + str(y[800]))
# Correlation should be around r = .98, essentially perfect.
print('Correlation: ' + str(stats.pearsonr(y[800:].flatten(), preds.flatten())[0]))