/** Parses the given exit policy string. */
void
Policy::fromString(QString policy)
{
/* Separate the action and the address/mask/port info */
QStringList ruleParts = policy.split(" ");
_action = toAction(ruleParts.at(0));
/* If some address/mask/port stuff was specified, parse it. */
if (ruleParts.size() > 1) {
QStringList addrParts = ruleParts.at(1).split(":");
/* Parse the address and mask (if specified) */
QString addr = addrParts.at(0);
_address.setAddress(addr.mid(0, addr.indexOf("/")));
if (_address.isNull()) {
_address = QHostAddress::Any;
}
if (addr.contains("/")) {
_mask = addr.mid(addr.indexOf("/")+1).toUInt();
}
/* Parse the specified port range (if specified) */
if (addrParts.size() > 1) {
QString ports = addrParts.at(1);
_fromPort = ports.mid(0, ports.indexOf("-")).toUInt();
if (ports.contains("-")) {
_toPort = ports.mid(ports.indexOf("-")+1).toUInt();
} else {
_toPort = _fromPort;
}
}
}
}
void offenseAgent(int port, int numTMates, int numEpi, double learnR,
int suffix, bool oppPres, double eps) {
// Number of features
int numF = oppPres ? (4 + 4 * numTMates) : (3 + 3 * numTMates);
// Number of actions
int numA = 2 + numTMates;
double discFac = 1;
// Tile coding parameter
double resolution = 0.1;
double range[numF];
double min[numF];
double res[numF];
for(int i = 0; i < numF; i++) {
min[i] = -1;
range[i] = 2;
res[i] = resolution;
}
// Weights file
char *wtFile;
std::string s = "weights_" + std::to_string(port) +
"_" + std::to_string(numTMates + 1) +
"_" + std::to_string(suffix);
wtFile = &s[0u];
double lambda = 0;
CMAC *fa = new CMAC(numF, numA, range, min, res);
SarsaAgent *sa = new SarsaAgent(numF, numA, learnR, eps, lambda, fa, wtFile, wtFile);
hfo::HFOEnvironment hfo;
hfo::status_t status;
hfo::action_t a;
double state[numF];
int action = -1;
double reward;
hfo.connectToServer(hfo::HIGH_LEVEL_FEATURE_SET,"../../bin/teams/base/config/formations-dt",6000,"localhost","base_left",false,"");
for (int episode=0; episode < numEpi; episode++) {
int count = 0;
status = hfo::IN_GAME;
action = -1;
while (status == hfo::IN_GAME) {
const std::vector<float>& state_vec = hfo.getState();
// If has ball
if(state_vec[5] == 1) {
if(action != -1) {
reward = getReward(status);
sa->update(state, action, reward, discFac);
}
// Fill up state array
purgeFeatures(state, state_vec, numTMates, oppPres);
// Get raw action
action = sa->selectAction(state);
// Get hfo::Action
a = toAction(action, state_vec);
} else {
a = hfo::MOVE;
}
if (a== hfo::PASS) {
hfo.act(a,state_vec[(9+6*numTMates) - (action-2)*3]);
//std::cout<<(9+6*numTMates) - (action-2)*3;
} else {
hfo.act(a);
}
status = hfo.step();
}
// End of episode
if(action != -1) {
reward = getReward(status);
sa->update(state, action, reward, discFac);
sa->endEpisode();
}
}
delete sa;
delete fa;
}
