void M2MFstAligner::_conditional_max( bool y_given_x ){
/*
Compute the conditional distribution, P(Y|X) using the WFST paradigm.
This is bassed on the approach from Shu and Hetherington 2002.
It is assumed that all WFSTs and operations use the Log semiring.
Given:
FST1 = P(X,Y)
Compute:
FST2 = P(X)
:= Map_inv(Det(RmEps(Proj_i(FST1))))
FST3 = P(Y|X)
:= Compose(FST2,FST1)
Proj_i: project on input labels
RmEps: epsilon removal
Det: determinize
Map_inv: invert weights
Notes: An analogous process may be used to compute P(X|Y). In this
case one would project on OUTPUT labels - Proj_o, and reverse the
composition order to Compose(FST1,FST2).
Future work:
What we are doing here in terms of *generating* the JOINT fst each
time is really just a dumb hack. We *should* encode the model in an
FST and encode the individual lattices, rather than doing the hacky
manual label encoding that we currently rely on.
*/
//Joint distribution that we start with
VectorFst<LogArc>* joint = new VectorFst<LogArc>();
SymbolTable* misyms = new SymbolTable("misyms");
SymbolTable* mosyms = new SymbolTable("mosyms");
joint->AddState();
joint->AddState();
joint->SetStart(0);
joint->SetFinal(1,LogArc::Weight::One());
map<LogArc::Label,LogWeight>::iterator it;
for( it=prev_alignment_model.begin(); it != prev_alignment_model.end(); it++ ){
string isym = isyms->Find((*it).first);
vector<string> io = tokenize_utf8_string( &isym, &s1s2_sep );
LogArc arc( misyms->AddSymbol(io[0]), mosyms->AddSymbol(io[1]), (*it).second, 1 );
joint->AddArc( 0, arc );
}
//VectorFst<LogArc>* joint = new VectorFst<LogArc>();
//Push<LogArc,REWEIGHT_TO_FINAL>(*_joint, joint, kPushWeights);
//joint->SetFinal(1,LogWeight::One());
joint->Write("m2mjoint.fst");
//BEGIN COMPUTE MARGINAL P(X)
VectorFst<LogArc>* dmarg;
if( y_given_x )
dmarg = new VectorFst<LogArc>(ProjectFst<LogArc>(*joint, PROJECT_INPUT));
else
dmarg = new VectorFst<LogArc>(ProjectFst<LogArc>(*joint, PROJECT_OUTPUT));
RmEpsilon(dmarg);
VectorFst<LogArc>* marg = new VectorFst<LogArc>();
Determinize(*dmarg, marg);
ArcMap(marg, InvertWeightMapper<LogArc>());
if( y_given_x )
ArcSort(marg, OLabelCompare<LogArc>());
else
ArcSort(marg, ILabelCompare<LogArc>());
//END COMPUTE MARGINAL P(X)
marg->Write("marg.fst");
//CONDITIONAL P(Y|X)
VectorFst<LogArc>* cond = new VectorFst<LogArc>();
if( y_given_x )
Compose(*marg, *joint, cond);
else
Compose(*joint, *marg, cond);
//cond now contains the conditional distribution P(Y|X)
cond->Write("cond.fst");
//Now update the model with the new values
for( MutableArcIterator<VectorFst<LogArc> > aiter(cond, 0); !aiter.Done(); aiter.Next() ){
LogArc arc = aiter.Value();
string lab = misyms->Find(arc.ilabel)+"}"+mosyms->Find(arc.olabel);
int labi = isyms->Find(lab);
alignment_model[labi] = arc.weight;
prev_alignment_model[labi] = LogWeight::Zero();
}
delete joint, marg, cond, dmarg;
delete misyms, mosyms;
return;
}
Move ChooseMove(const GameState& game, unsigned iterations)
{
std::mt19937 r(GlobalRandomDevice());
MCTSNode root;
MCTSNode* store = (MCTSNode*)malloc(sizeof(MCTSNode) * iterations);
MCTSNode* store_head = store;
for (unsigned iter = 0; iter < iterations; ++iter)
{
GameState sim_state = Determinize(game, r);
// Selection
MCTSNode* node = &root;
while (!node->HasUntriedMoves(sim_state) && node->HasChildren())
{
MCTSNode* next_node = node->UCTSelectChild(sim_state);
// Update availability
for (MCTSNode* avail_node = node->m_child; avail_node; avail_node = avail_node->m_siblings)
{
if (sim_state.m_possible_moves.Contains(avail_node->m_move))
{
avail_node->m_availability++;
}
}
sim_state.ProcessMove(next_node->m_move);
node = next_node;
}
// Expansion
if (node->HasUntriedMoves(sim_state))
{
Move m = node->ChooseRandomUntriedMove(sim_state, r);
for (MCTSNode* avail_node = node->m_child; avail_node; avail_node = avail_node->m_siblings)
{
if (sim_state.m_possible_moves.Contains(avail_node->m_move))
{
avail_node->m_availability++;
}
}
sim_state.ProcessMove(m);
node = node->AddChild(m, store_head);
store_head += 1;
node->m_availability++;
}
// Simulation
sim_state.PlayOutRandomly(r);
// Backpropagation
bool won = sim_state.m_winner == (Winner)game.m_active_player_index;
while (node)
{
node->m_visits++;
if (won) node->m_wins++;
node = node->m_parent;
}
}
MCTSNode* best_node = nullptr;
uint32_t best_visits = 0;
for (MCTSNode* node = root.m_child; node; node = node->m_siblings)
{
if (node->m_visits > best_visits)
{
best_visits = node->m_visits;
best_node = node;
}
}
Move m = best_node->m_move;
free(store);
return m;
}
