void POCMAN::MoveGhostDefensive(POCMAN_STATE& pocstate, int g) const
{
if (Bernoulli(DefensiveSlip) && pocstate.GhostDir[g] >= 0)
{
pocstate.GhostDir[g] = -1;
return;
}
int bestDist = 0;
COORD bestPos = pocstate.GhostPos[g];
int bestDir = -1;
for (int dir = 0; dir < 4; dir++)
{
int dist = COORD::DirectionalDistance(
pocstate.PocmanPos, pocstate.GhostPos[g], dir);
COORD newpos = NextPos(pocstate.GhostPos[g], dir);
if (dist >= bestDist && newpos.Valid()
&& COORD::Opposite(dir) != pocstate.GhostDir[g])
{
bestDist = dist;
bestPos = newpos;
}
}
pocstate.GhostPos[g] = bestPos;
pocstate.GhostDir[g] = bestDir;
}
void POCMAN::GeneratePreferred(const STATE& state, const HISTORY& history,
vector<int>& actions, const STATUS& status) const
{
const POCMAN_STATE& pocstate = safe_cast<const POCMAN_STATE&>(state);
if (history.Size())
{
int action = history.Back().Action;
int observation = history.Back().Observation;
// If power pill and can see a ghost then chase it
if (pocstate.PowerSteps > 0 && (observation & 15 != 0))
{
for (int a = 0; a < 4; ++a)
if (CheckFlag(observation, a))
actions.push_back(a);
}
// Otherwise avoid observed ghosts and avoid changing directions
else
{
for (int a = 0; a < 4; ++a)
{
COORD newpos = NextPos(pocstate.PocmanPos, a);
if (newpos.Valid() && !CheckFlag(observation, a)
&& COORD::Opposite(a) != action)
actions.push_back(a);
}
}
}
}
void POCMAN::MoveGhostAggressive(POCMAN_STATE& pocstate, int g) const
{
if (!Bernoulli(ChaseProb))
{
MoveGhostRandom(pocstate, g);
return;
}
int bestDist = Maze.GetXSize() + Maze.GetYSize();
COORD bestPos = pocstate.GhostPos[g];
int bestDir = -1;
for (int dir = 0; dir < 4; dir++)
{
int dist = COORD::DirectionalDistance(
pocstate.PocmanPos, pocstate.GhostPos[g], dir);
COORD newpos = NextPos(pocstate.GhostPos[g], dir);
if (dist <= bestDist && newpos.Valid()
&& COORD::Opposite(dir) != pocstate.GhostDir[g])
{
bestDist = dist;
bestPos = newpos;
}
}
pocstate.GhostPos[g] = bestPos;
pocstate.GhostDir[g] = bestDir;
}
void POCMAN::GenerateLegal(const STATE& state, const HISTORY& history,
vector<int>& legal, const STATUS& status) const
{
const POCMAN_STATE& pocstate = safe_cast<const POCMAN_STATE&>(state);
// Don't move into walls
for (int a = 0; a < 4; ++a)
{
COORD newpos = NextPos(pocstate.PocmanPos, a);
if (newpos.Valid())
legal.push_back(a);
}
}
void POCMAN::MoveGhostRandom(POCMAN_STATE& pocstate, int g) const
{
// Never switch to opposite direction
// Currently assumes there are no dead-ends.
COORD newpos;
int dir;
do
{
dir = Random(4);
newpos = NextPos(pocstate.GhostPos[g], dir);
}
while (COORD::Opposite(dir) == pocstate.GhostDir[g] || !newpos.Valid());
pocstate.GhostPos[g] = newpos;
pocstate.GhostDir[g] = dir;
}
int POCMAN::MakeObservations(const POCMAN_STATE& pocstate) const
{
int observation = 0;
for (int d = 0; d < 4; d++)
{
if (SeeGhost(pocstate, d) >= 0)
SetFlag(observation, d);
COORD wpos = NextPos(pocstate.PocmanPos, d);
if (wpos.Valid() && Passable(wpos))
SetFlag(observation, d + 4);
}
if (SmellFood(pocstate))
SetFlag(observation, 8);
if (HearGhost(pocstate))
SetFlag(observation, 9);
return observation;
}
bool POCMAN::Step(STATE& state, int action,
int& observation, double& reward) const
{
POCMAN_STATE& pocstate = safe_cast<POCMAN_STATE&>(state);
reward = RewardDefault;
observation = 0;
// cout << COORD::CompassChar[action];
COORD newpos = NextPos(pocstate.PocmanPos, action);
if (newpos.Valid())
pocstate.PocmanPos = newpos;
else
reward += RewardHitWall;
if (pocstate.PowerSteps > 0)
pocstate.PowerSteps--;
int hitGhost = -1;
for (int g = 0; g < NumGhosts; g++)
{
if (pocstate.GhostPos[g] == pocstate.PocmanPos)
hitGhost = g;
MoveGhost(pocstate, g);
if (pocstate.GhostPos[g] == pocstate.PocmanPos)
hitGhost = g;
}
if (hitGhost >= 0)
{
if (pocstate.PowerSteps > 0)
{
reward += RewardEatGhost;
pocstate.GhostPos[hitGhost] = GhostHome;
pocstate.GhostDir[hitGhost] = -1;
}
else
{
reward += RewardDie;
return true;
}
}
observation = MakeObservations(pocstate);
int pocIndex = Maze.Index(pocstate.PocmanPos);
if (pocstate.Food[pocIndex])
{
pocstate.Food[pocIndex] = false;
pocstate.NumFood--;
if (pocstate.NumFood == 0)
{
reward += RewardClearLevel;
return true;
}
if (CheckFlag(Maze(pocstate.PocmanPos.X, pocstate.PocmanPos.Y), E_POWER))
pocstate.PowerSteps = PowerNumSteps;
reward += RewardEatFood;
}
return false;
}
