GTP command uct_policy_moves_simple; add playout policy tests

git-svn-id: svn://svn.code.sf.net/p/fuego/code/trunk@1967 2e953b5c-c64d-0410-be54-f773e93e544c

gouct/GoUctCommands.cpp

@@ -324,6 +324,7 @@ void GoUctCommands::AddGoGuiAnalyzeCommands(GtpCommand& cmd)
         "plist/Uct Patterns/uct_patterns\n"
         "pstring/Uct Policy Corrected Moves/uct_policy_corrected_moves\n"
         "pstring/Uct Policy Moves/uct_policy_moves\n"
+        "pstring/Uct Policy Moves Simple List/uct_policy_moves_simple\n"
         "gfx/Uct Prior Knowledge/uct_prior_knowledge\n"
         "sboard/Uct Rave Values/uct_rave_values\n"
         "plist/Uct Root Filter/uct_root_filter\n"
@@ -1093,7 +1094,7 @@ void GoUctCommands::CmdPolicyCorrectedMoves(GtpCommand& cmd)
     See GoUctPlayoutPolicy::GetEquivalentBestMoves() <br>
     Arguments: none <br>
     Returns: Move type string followed by move list on a single line. */
-void GoUctCommands::CmdPolicyMoves(GtpCommand& cmd)
+void GoUctCommands::WritePolicyMoves(GtpCommand& cmd, bool writeGammas)
 {
     cmd.CheckArgNone();
     GoUctPlayoutPolicy<GoBoard> policy(m_bd, Player().m_playoutPolicyParam);
@@ -1111,10 +1112,30 @@ void GoUctCommands::CmdPolicyMoves(GtpCommand& cmd)
     if (policy.MoveType() == GOUCT_GAMMA_PATTERN)
     {
         cmd << ' ';
-        policy.GammaGenerator().WriteMovesAndGammas(cmd);
+        policy.GammaGenerator().WriteMovesAndGammas(cmd, writeGammas);
     }
 }
 
+/** Return equivalent best moves in playout policy.
+ See GoUctPlayoutPolicy::GetEquivalentBestMoves() <br>
+ Arguments: none <br>
+ Returns: Move type string followed by move list on a single line. 
+ For non-uniform generators, also write selection weights (gammas)
+*/
+void GoUctCommands::CmdPolicyMoves(GtpCommand& cmd)
+{
+    WritePolicyMoves(cmd, true); // do write move weights (gammas)
+}
+
+/** Return equivalent best moves in playout policy.
+ See GoUctPlayoutPolicy::GetEquivalentBestMoves() <br>
+ Arguments: none <br>
+ Returns: Move type string followed by move list on a single line. */
+void GoUctCommands::CmdPolicyMovesSimple(GtpCommand& cmd)
+{
+    WritePolicyMoves(cmd, false); // don't write move weights (gammas)
+}
+
 /** Show total prior knowledge */
 void GoUctCommands::CmdPriorKnowledge(GtpCommand& cmd)
 {
@@ -1652,6 +1673,8 @@ void GoUctCommands::Register(GtpEngine& e)
     Register(e, "uct_policy_corrected_moves",
              &GoUctCommands::CmdPolicyCorrectedMoves);
     Register(e, "uct_policy_moves", &GoUctCommands::CmdPolicyMoves);
+    Register(e, "uct_policy_moves_simple",
+             &GoUctCommands::CmdPolicyMovesSimple);
     Register(e, "uct_prior_knowledge", &GoUctCommands::CmdPriorKnowledge);
     Register(e, "uct_rave_values", &GoUctCommands::CmdRaveValues);
     Register(e, "uct_root_filter", &GoUctCommands::CmdRootFilter);

gouct/GoUctCommands.h

@@ -75,6 +75,7 @@ class GoUctCommands
         - @link CmdPolicyCorrectedMoves() @c uct_policy_corrected_moves 
           @endlink
         - @link CmdPolicyMoves() @c uct_policy_moves @endlink
+        - @link CmdPolicyMovesSimple() @c uct_policy_moves_simple @endlink
         - @link CmdPriorKnowledge() @c uct_prior_knowledge @endlink
         - @link CmdRaveValues() @c uct_rave_values @endlink
         - @link CmdRootFilter() @c uct_root_filter @endlink
@@ -118,6 +119,7 @@ class GoUctCommands
     void CmdPatterns(GtpCommand& cmd);
     void CmdPolicyCorrectedMoves(GtpCommand& cmd);
     void CmdPolicyMoves(GtpCommand& cmd);
+    void CmdPolicyMovesSimple(GtpCommand& cmd);
     void CmdPriorKnowledge(GtpCommand& cmd);
     void CmdRaveValues(GtpCommand& cmd);
     void CmdRootFilter(GtpCommand& cmd);
@@ -187,6 +189,8 @@ class GoUctCommands
 
     GoUctGlobalSearchState<GoUctPlayoutPolicy<GoUctBoard> >&
     ThreadState(unsigned int threadId);
+
+    void WritePolicyMoves(GtpCommand& cmd, bool writeGammas);
 };
 
 //----------------------------------------------------------------------------

gouct/GoUctGammaMoveGenerator.h

@@ -29,7 +29,7 @@ class GoUctGammaMoveGenerator
 
     int NuMoves() const;
 
-    void WriteMovesAndGammas(std::ostream& stream) const;
+    void WriteMovesAndGammas(std::ostream& stream, bool writeGammas) const;
 
 private:
     /** Generate pattern moves with gamma values */
@@ -222,12 +222,15 @@ std::ostream& operator<<(std::ostream& stream,
 
 template<class BOARD>
 void GoUctGammaMoveGenerator<BOARD>::
-	 WriteMovesAndGammas(std::ostream& stream) const
+	 WriteMovesAndGammas(std::ostream& stream, bool writeGammas) const
 {
     for (int i = 0; i < NuMoves(); ++i)
     {
-        stream << SgWritePoint(GetGammaMoveAt(i)) << ":"
-               << GetGammaValueForMoveAt(i) << "  ";
+        stream << SgWritePoint(GetGammaMoveAt(i));
+        if (writeGammas)
+            stream << ":"
+                   << GetGammaValueForMoveAt(i);
+        stream << ' ';
     }
     stream << std::endl;
 }

regression/Makefile.am

@@ -397,7 +397,11 @@ sgf/playout/playout_atari_defense_1.sgf \
 sgf/playout/playout_atari_defense_2.sgf \
 sgf/playout/playout_atari_defense_3.sgf \
 sgf/playout/playout_capture_1.sgf \
+sgf/playout/playout_capture_no_selfatari.1.sgf \
+sgf/playout/playout_capture_no_selfatari.2.sgf \
 sgf/playout/playout_nakade.1.sgf \
+sgf/playout/playout_nakade.2.sgf \
+sgf/playout/playout_nakade.3.sgf \
 sgf/playout/playout_nakade_approach.sgf \
 sgf/playout/playout_two_liberties_semeai.1.sgf \
 sgf/playout/playout_two_liberties_semeai.2.sgf \

regression/playout_atari_capture.tst

@@ -47,3 +47,23 @@ loadsgf sgf/playout/playout_two_liberties_semeai.3.sgf 4
 201 uct_policy_moves
 #? [AtariCapture J7]*
 # current policy captures F4...
+
+#-----------------------------------------------------------------------------
+# Good capture vs. Selfatari capture
+
+loadsgf sgf/playout/playout_capture_no_selfatari.1.sgf
+210 reg_genmove w
+#? [H2]
+
+211 uct_policy_moves
+#? [AtariCapture H2]*
+# current policy captures J8, selfatari
+
+loadsgf sgf/playout/playout_capture_no_selfatari.2.sgf
+220 reg_genmove w
+#? [H2]*
+
+221 uct_policy_moves
+#? [AtariCapture H2]*
+# current policy captures J8, selfatari
+

regression/playout_nakade.tst

@@ -29,6 +29,14 @@ loadsgf sgf/playout/playout_nakade.1.sgf 7
 #? [J8]
 # must kill on vital point.
 
-31 uct_policy_moves
-#? [Pattern J8]
-# Should be different move reason in future ???
+31 uct_policy_moves_simple
+#? [GammaPattern J8]
+# Should be different move reason in future ???
+
+loadsgf sgf/playout/playout_nakade.2.sgf
+40 uct_policy_moves
+#? [GammaPattern E1:1 F1:550.309]
+# F1 is much more likely, but E1 would be fatal...
+
+41 uct_policy_moves_simple
+#? [GammaPattern F1]*

regression/sgf/playout/playout_capture_no_selfatari.1.sgf

@@ -0,0 +1,5 @@
+(;FF[4]CA[UTF-8]AP[GoGui:1.4.9]SZ[9]
+KM[0.5]DT[2014-12-16]
+AB[ae][bf][be][ce][cd][cc][df][de][ee][ed][ec][eb][ff][fd][fb][fa][gi][gh][gf][gd][hi][hg][hf][hb][ii][ih]
+AW[ag][af][bg][ch][cg][cf][dg][eg][ef][fi][fh][fg][fe][fc][gg][ge][gc][gb][ga][he][hd][hc][ha][ig][if][ie][id][ic][ia]
+PL[W])

regression/sgf/playout/playout_capture_no_selfatari.2.sgf

@@ -0,0 +1,5 @@
+(;FF[4]CA[UTF-8]AP[GoGui:1.4.9]SZ[9]
+KM[0.5]DT[2014-12-16]
+AB[ae][bf][be][ce][cd][cc][df][de][ee][ed][ec][eb][ff][fd][fb][fa][gi][gh][gf][gd][hi][hg][hf][ii][ih]
+AW[ag][af][bg][ch][cg][cf][dg][eg][ef][fi][fh][fg][fe][fc][gg][ge][gc][gb][ga][he][hd][hc][ha][ig][if][ie][id][ic][ia]
+PL[B];B[hb])

regression/sgf/playout/playout_nakade.2.sgf

@@ -0,0 +1,3 @@
+(;FF[4]CA[UTF-8]AP[GoGui:1.4.9]SZ[9]
+KM[7.5]DT[2014-12-16]
+AB[di][dh][eh][eg][ef][ff][gf][gg][gh][gi]PL[W];W[fh])

regression/sgf/playout/playout_nakade.3.sgf

@@ -0,0 +1,3 @@
+(;FF[4]CA[UTF-8]AP[GoGui:1.4.9]SZ[9]
+KM[7.5]DT[2014-12-16]
+AB[di][dh][eh][eg][ef][ff][gf][gg][gh][gi]PL[W];W[fi])