Santara

#!/usr/bin/env python

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import collections
import json
import os

Santara

Experiment 1

Motivation

Train a single agent to drive three cars in Alpine

Details

• Action space: steering-acceleration-brake
• Car models:

Santara

"""
Gym Madras Env Wrapper.

This is an OpenAI gym environment wrapper for the MADRaS simulator. For more information on the OpenAI Gym interface, please refer to: https://gym.openai.com

Built on top of gym_torcs https://github.com/ugo-nama-kun/gym_torcs/blob/master/gym_torcs.py

The following enhancements were made for Multi-agent synchronization using exception handling:
- All the agents connect to the same TORCS engine through UDP ports
- If an agent fails to connect to the TORCS engine, it keeps on trying in a loop until successful

Santara

import os
from glob import glob
import shutil

root_dir = '.'
for dir in glob(root_dir+'/*'):
    dir_name = dir.split('/')[-1]
    if os.path.exists(os.path.join(dir, 'log1.csv')):
        shutil.copy2(os.path.join(dir, 'log1.csv'), os.path.join(root_dir, 'logdump', dir_name+'.csv'))

Santara

"""
Gym interface to snakeoil3_gym.py.

Provides a gym interface to the traditional server-client model.
"""
import os
import subprocess
from mpi4py import MPI
import time

Santara

import numpy as np
import sys

def ssv2csv(tsv_filename):
    """Converts tab-separated variables into comma-separated variables.
    """
    f_in = open(tsv_filename, 'r')
    f_out = open(tsv_filename.split('.')[0]+'.csv', 'w')
    for line in f_in:
        csv_line = line.strip().split('\t')

Santara

import numpy as np 

def hcope_estimator(X, c, delta):
	"""
	X : float, size = (size_of_history, )
		importance weighted trajectory rewards from the behavior policy 
	c : float, size = (size_of_history, )
					= scalar, if all samples from X have the same threshold
		thresholds for each random variable in x
	delta : float, size = scalar

Santara

import tensorflow as tf
import numpy as np

inputs1 = tf.placeholder(shape=[1,16],dtype=tf.float32)
W = tf.Variable(tf.random_uniform([16,4],0,0.01))
Qout = tf.matmul(inputs1,W)
grad_Qout_inputs1 = tf.gradients(Qout, inputs1)

init = tf.initialize_all_variables()
sess = tf.Session()

Santara

   model_G = nn.Sequential()
   model_G:add(nn.JoinTable(2, 2))
   model_G:add(cudnn.SpatialConvolutionUpsample(3+1, 64, 7, 7, 1, 1)):add(cudnn.ReLU(true))
   model_G:add(nn.SpatialBatchNormalization(64, nil, nil, false))
   model_G:add(cudnn.SpatialConvolutionUpsample(64, 368, 7, 7, 1, 4)):add(cudnn.ReLU(true))
   model_G:add(nn.SpatialBatchNormalization(368, nil, nil, false))
   model_G:add(nn.SpatialDropout(0.5))
   model_G:add(cudnn.SpatialConvolutionUpsample(368, 128, 7, 7, 1, 4)):add(cudnn.ReLU(true))
   model_G:add(nn.SpatialBatchNormalization(128, nil, nil, false))
   model_G:add(nn.FeatureLPPooling(2,2,2,true))

Santara

----------------------------------------------------------------------
-- CIFAR 8x8
opt.scale = 8 
opt.geometry = {3, opt.scale, opt.scale}
local input_sz = opt.geometry[1] * opt.geometry[2] * opt.geometry[3]
local numhid = 600 
model_D = nn.Sequential()
model_D:add(nn.Reshape(input_sz))
model_D:add(nn.Linear(input_sz, numhid))
model_D:add(nn.ReLU())