Add recursive search depth, remove FPU VL bug

src/Parameters.cpp

@@ -89,7 +89,7 @@ void Parameters::setup_default_parameters() {
 #endif
     cfg_puct = 0.6f;
     cfg_softmax_temp = 1.0f;
-    cfg_fpu_reduction = 0.0f;
+    cfg_fpu_reduction = 0.1f;
     cfg_fpu_dynamic_eval = true;
     cfg_root_temp_decay = 0;
     cfg_min_resign_moves = 20;

src/UCTNode.cpp

@@ -354,7 +354,7 @@ UCTNode* UCTNode::uct_select_child(Color color, bool is_root) {
 
     // Estimated eval for unknown nodes = original parent NN eval - reduction
     // Or curent parent eval - reduction if dynamic_eval is enabled.
-    auto fpu_eval = (cfg_fpu_dynamic_eval ? get_eval(color) : net_eval) - fpu_reduction;
+    auto fpu_eval = (cfg_fpu_dynamic_eval ? get_raw_eval(color) : net_eval) - fpu_reduction;
 
     for (const auto& child : m_children) {
         if (!child->active()) {

src/UCTSearch.cpp

@@ -59,13 +59,16 @@ void UCTSearch::set_quiet(bool quiet) {
     quiet_ = quiet;
 }
 
-SearchResult UCTSearch::play_simulation(BoardHistory& bh, UCTNode* const node) {
+SearchResult UCTSearch::play_simulation(BoardHistory& bh, UCTNode* const node, int ndepth) {
     const auto& cur = bh.cur();
     const auto color = cur.side_to_move();
 
     auto result = SearchResult{};
 
     node->virtual_loss();
+    if (ndepth > m_maxdepth) {
+        m_maxdepth = ndepth;
+    }
 
     if (!node->has_children()) {
         bool drawn = cur.is_draw();
@@ -102,7 +105,7 @@ SearchResult UCTSearch::play_simulation(BoardHistory& bh, UCTNode* const node) {
         auto next = node->uct_select_child(color, node == m_root.get());
         auto move = next->get_move();
         bh.do_move(move);
-        result = play_simulation(bh, next);
+        result = play_simulation(bh, next, ndepth+1);
     }
 
     if (result.valid()) {
@@ -266,8 +269,7 @@ void UCTSearch::dump_analysis(int64_t elapsed, bool force_output) {
     float feval = m_root->get_raw_eval(color);
     // UCI-like output wants a depth and a cp, so convert winrate to a cp estimate.
     int cp = 290.680623072 * tan(3.096181612 * (feval - 0.5));
-    // same for nodes to depth, assume nodes = 1.8 ^ depth.
-    int depth = log(float(m_nodes)) / log(1.8);
+    int depth = m_maxdepth;
     // To report nodes, use visits.
     //   - Only includes expanded nodes.
     //   - Includes nodes carried over from tree reuse.
@@ -364,7 +366,7 @@ bool UCTSearch::pv_limit_reached() const {
 void UCTWorker::operator()() {
     do {
         BoardHistory bh = bh_.shallow_clone();
-        auto result = m_search->play_simulation(bh, m_root);
+        auto result = m_search->play_simulation(bh, m_root, 0);
         if (result.valid()) {
             m_search->increment_playouts();
         }
@@ -390,6 +392,7 @@ Move UCTSearch::think(BoardHistory&& new_bh) {
     }
 
     m_playouts = 0;
+    m_maxdepth = 0;
     m_nodes = m_root->count_nodes();
     m_tbhits = 0;
     // TODO: Both UCI and the next line do shallow_clone.
@@ -447,13 +450,12 @@ Move UCTSearch::think(BoardHistory&& new_bh) {
     int last_update = 0;
     do {
         auto currstate = bh_.shallow_clone();
-        auto result = play_simulation(currstate, m_root.get());
+        auto result = play_simulation(currstate, m_root.get(), 0);
         if (result.valid()) {
             increment_playouts();
         }
 
-        // assume nodes = 1.8 ^ depth.
-        int depth = log(float(m_nodes)) / log(1.8);
+        int depth = m_maxdepth;
         if (depth != last_update) {
             last_update = depth;
             dump_analysis(Time.elapsed(), false);
@@ -506,7 +508,7 @@ void UCTSearch::ponder() {
     }
     do {
         auto bh = bh_.shallow_clone();
-        auto result = play_simulation(bh, m_root.get());
+        auto result = play_simulation(bh, m_root.get(), 0);
         if (result.valid()) {
             increment_playouts();
         }

src/UCTSearch.h

@@ -81,7 +81,7 @@ class UCTSearch {
     void increment_playouts();
     bool should_halt_search();
     void please_stop();
-    SearchResult play_simulation(BoardHistory& bh, UCTNode* const node);
+    SearchResult play_simulation(BoardHistory& bh, UCTNode* const node, int sdepth);
 
 private:
     void dump_stats(BoardHistory& pos, UCTNode& parent);
@@ -95,6 +95,7 @@ class UCTSearch {
     std::unique_ptr<UCTNode> m_root;
     std::atomic<int> m_nodes{0};
     std::atomic<int> m_playouts{0};
+    std::atomic<int> m_maxdepth{0};
     std::atomic<int> m_tbhits{0};
     int64_t m_target_time{0};
     int64_t m_max_time{0};

src/config.h

@@ -37,7 +37,7 @@
 #endif
 static constexpr int SELFCHECK_PROBABILITY = 2000;
 static constexpr int SELFCHECK_MIN_EXPANSIONS = 2'000'000;
-//#define USE_TUNER
+#define USE_TUNER
 
 #define PROGRAM_VERSION "v0.7"
 

src/main.cpp

@@ -101,6 +101,7 @@ static std::string parse_commandline(int argc, char *argv[]) {
 #endif
 #ifdef USE_TUNER
         ("puct", po::value<float>())
+        ("fpu_reduction", po::value<float>())
         ("softmax_temp", po::value<float>())
 #endif
         ;
@@ -150,6 +151,9 @@ static std::string parse_commandline(int argc, char *argv[]) {
     if (vm.count("puct")) {
         cfg_puct = vm["puct"].as<float>();
     }
+    if (vm.count("fpu_reduction")) {
+        cfg_fpu_reduction = vm["fpu_reduction"].as<float>();
+    }
     if (vm.count("softmax_temp")) {
         cfg_softmax_temp = vm["softmax_temp"].as<float>();
     }