tigerneil

Understanding LSTMs

• Japanese: qiita
• Russian: Alex Sosn
• Chinese: jianshu, csdn, csdn, csdn,

tigerneil

package thunder.streaming

import org.apache.spark.{SparkConf, Logging}
import org.apache.spark.rdd.RDD
import org.apache.spark.SparkContext._
import org.apache.spark.streaming._
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.mllib.clustering.KMeansModel

import scala.util.Random.nextDouble

tigerneil

from keras.layers import GRU, initializations, K
from collections import OrderedDict

class GRULN(GRU):
    '''Gated Recurrent Unit with Layer Normalization
    Current impelemtation only works with consume_less = 'gpu' which is already
    set.

    # Arguments
        output_dim: dimension of the internal projections and the final output.

tigerneil

Code for Keras plays catch blog post

Train

python qlearn.py

Test

1. Generate figures

tigerneil

from __future__ import print_function
from __future__ import absolute_import
import os

os.environ['THEANO_FLAGS'] = 'device=cpu,mode=FAST_COMPILE,optimizer=None'

from rllab.algos.ddpg import DDPG
from rllab.envs.box2d.cartpole_env import CartpoleEnv
from rllab.policies.deterministic_mlp_policy import DeterministicMLPPolicy
from rllab.q_functions.continuous_mlp_q_function import ContinuousMLPQFunction

tigerneil

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

tigerneil

Prioritized Experience Replay

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 42 out of 57 games.

Authors: Tom Schaul [email protected], John Quan [email protected], Ioannis Antonoglou [email protected], David Silver [email protected]

Recurrent Reinforcement Learning: A Hybrid Ap

tigerneil

"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code

class LSTM:
  
  @staticmethod
  def init(input_size, hidden_size, fancy_forget_bias_init = 3):

tigerneil

"""
Simple implementation of Identity Recurrent Neural Networks (IRNN)

Reference
    A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
    http://arxiv.org/abs/1504.00941

"""

import numpy as np

tigerneil

import theano
from pylearn2.models import mlp
from pylearn2.training_algorithms import sgd
from pylearn2.termination_criteria import EpochCounter
from pylearn2.datasets.dense_design_matrix import DenseDesignMatrix
import numpy as np
from random import randint


class XOR(DenseDesignMatrix):