diff options
| author | tslil clingman <tslil@posteo.de> | 2023-01-15 21:31:00 +0100 |
|---|---|---|
| committer | tslil <tslil@posteo.de> | 2026-08-28 19:37:41 +0100 |
| commit | 0223a9bec5535fced1a7698b55fd42155d9b0446 (patch) | |
| tree | e7a980454e65d88b56194eed733cabec29ef51b5 /include/actions.c | |
| parent | ee216c008a188a9436fedb85c70ee5d1719733b1 (diff) | |
switch to explicit game state & important bug fix & clang format
Previously the code base assumed that there was a single, global game
state which was the implicit target of all actions taken. Looking
ahead at architectural improvements, this has now been (almost
entirely) made explicit and functions take tak_state_p where
necessary (and also where unnecessary).
Two important fixes to actions.c were made:
- Previously when generating the possible stack moves, stack height
overflows (> 15) were not taken into account and this resulted in the
tree search corrupting the board state. Now action search does not
list all legal actions, rather the subset of these encodeable by the
implementation.
- The check for crushing on a stack move was incorrect (too strict),
and this resulted in many legitimate moves being igonored.
Finally, in other changes, weights have also been improved by training
all games instead of some subset for chosen players, and clang-format
was run on the codebase.
Diffstat (limited to 'include/actions.c')
| -rw-r--r-- | include/actions.c | 508 |
1 files changed, 276 insertions, 232 deletions
diff --git a/include/actions.c b/include/actions.c index 795c135..6303822 100644 --- a/include/actions.c +++ b/include/actions.c @@ -16,37 +16,42 @@ */ #include "actions.h" +#include "tak.h" + +#include <stdio.h> + +static uint8_t al_board_size; // =================================================================== // Helper method declarations // =================================================================== -#define DANGER_MIN(a,b) (((a)<(b))?(a):(b)) +#define DANGER_MIN(a, b) (((a) < (b)) ? (a) : (b)) #define CLR_STONE NUM_MASK -static inline void -list_append(action_list_t *list, const enum A_TYPE type, - const int8_t loc, const uint8_t data0, - const uint8_t data1); +static inline void list_append(action_list_t *list, const enum A_TYPE type, + const int8_t loc, const uint8_t data0, + const uint8_t data1); + +static inline void list_prepend(action_list_t *list, const enum A_TYPE type, + const int8_t loc, const uint8_t data0, + const uint8_t data1); -static inline void -list_prepend(action_list_t *list, const enum A_TYPE type, - const int8_t loc, const uint8_t data0, - const uint8_t data1); +static inline void inline_next_ply(tak_state_p state); -static inline void -inline_next_ply(void); +static inline void inline_prev_ply(tak_state_p state); -static inline void -inline_prev_ply(void); +static inline uint8_t check_no_overflow(tak_state_p state, const uint8_t loc, + const int8_t delta, const uint8_t num, + const uint8_t steps, + const uint8_t gaps); // =================================================================== // Exported method implementations // =================================================================== -int action_move_to_front(const action_t action, - action_list_t *list) { +int action_move_to_front(const action_t action, action_list_t *list) { action_node_t *n = list->head; // TODO: what if it's not in the list? @@ -64,7 +69,6 @@ int action_move_to_front(const action_t action, return EXIT_FAILURE; } - void action_list_free(action_list_t *list) { if (list) { action_node_t *n = list->head, *nn; @@ -80,7 +84,8 @@ void action_list_free(action_list_t *list) { // Keep track of move offsets int8_t move_deltas[4]; -void action_list_init(void) { +void action_list_init(const uint8_t board_size) { + al_board_size = board_size; move_deltas[0] = +board_size; move_deltas[1] = -board_size; move_deltas[2] = -1; @@ -89,7 +94,7 @@ void action_list_init(void) { // We bias place over move by prepending place actions and appending // move actions to the generated list -action_list_t *action_list_generate(void) { +action_list_t *action_list_generate(tak_state_p state) { action_list_t *list = malloc(sizeof(struct action_list_s)); // TODO: trap errno @@ -103,278 +108,297 @@ action_list_t *action_list_generate(void) { * well save on the conditional. */ - const uint8_t material = (ply & 1) ? black_count : white_count, - flat = material & 0x7F, - cap = ((ply >= 2) && (material & 0x80)), - standing = ((ply >= 2) && flat); + const uint8_t material = + (state->ply & 1) ? state->black_count : state->white_count, + flat = material & 0x7F, + cap = ((state->ply >= 2) && (material & 0x80)), + standing = ((state->ply >= 2) && flat); // Step across the board - for (int row = 0; row < board_size; row++) { - for (int col = 0; col < board_size; col++) { + for (int row = 0; row < state->board_size; row++) { + for (int col = 0; col < state->board_size; col++) { // We'll need these at various points: the location of this // square and the maximum number of stones we could pick up - const int loc = THE_COORDS(col, row); - const uint8_t count = DANGER_MIN(COUNT_AT(loc), board_size); + const int loc = THE_COORDS(al_board_size, col, row); + const uint8_t count = DANGER_MIN(COUNT_AT(state, loc), al_board_size); // Only try moves after CPS and if the colour is correct if (count) { - if (ply >= 2 && ((colours[loc] & 1) == current_colour)) { - - // Pre-compute end-stops and crushes - uint8_t end_stops[4], crushes[4] = {0, 0, 0, 0}; - - // These are upper bounds, not counting walls and such. - // UP DOWN LEFT RIGHT - end_stops[0] = DANGER_MIN(board_size - row - 1, count); - end_stops[1] = DANGER_MIN(row, count); - end_stops[2] = DANGER_MIN(col, count); - end_stops[3] = DANGER_MIN(board_size - col - 1, count); - - // Now we check for caps and walls - const uint8_t cap_top = STONE_AT(loc) == STONE_CAPSTONE; - for (int d = 0; d < 4; d++){ - const int delta = move_deltas[d]; - const int stop = end_stops[d]; - end_stops[d] = 0; - for (int k = 1; k <= stop; k++) { - const enum STONE_VARIANT stone = STONE_AT(loc+k*delta); - if (stone == STONE_STANDING) { - if (cap_top) { - crushes[d] = 0xFF; - end_stops[d]++; - } - break; - } else if (stone == STONE_CAPSTONE) { - break; - } - end_stops[d]++; - } - } - /* - * For each direction, generate all possible ordered integer - * partitions of 1 ≤ num ≤ count whose number of summands is - * exactly 1 ≤ summands ≤ min(end_stops[dir], num) -- we - * write summands as steps. - * - * We exploit the `gaps' bijection here and elsewhere - * between ordered {integer partitions of n with s summands} - * and {binary strings of length n-1 with s-1 set bits}. - */ - for (enum MOVE_DIRECTION dir=M_UP; dir<=M_RIGHT; dir++) { - for (uint8_t num = 1; num <= count; num++) { - for (uint8_t steps = 1; - steps <= end_stops[dir] && steps <= num; - steps++) { - uint8_t gaps = - ((1<<(board_size - 2)) - 1) >> (board_size-steps-1); - // For 5x5 this givess 0b0000[0XXX] where steps-1 of - // those X's are 1s (starting with LSB) because 4-1=3 - // and 5-1=4 - do { - /* - * We skip the partition if it calls for multiple - * stones at the end with a crush. - */ - const uint8_t last_drop_check = - (num > 1) ? (gaps & (1 << (num - 2))) : 1; - if (crushes[dir] == 0 || last_drop_check) { - // We have to record a crush! - const uint8_t crush = - (steps == end_stops[dir]) && crushes[dir]; - // Store the move - - list_append(list, A_MOVE, loc, - (crush << 7) | gaps, - (dir<<4) | num); - } - /* - * With thanks to - * https://graphics.stanford.edu/~seander/bithacks.html#NextBitPermutation - * we have the following magic to generate the next - * permutation of steps-many set bits - */ - uint8_t t = (gaps | (gaps - 1)); - gaps = (t + 1) - | (((~t & -~t) - 1) >> (__builtin_ctz(gaps) + 1)); - } while (gaps && (gaps + 1 <= (1 << (num - 1)))); - } - } - } - } + if (state->ply >= 2 && + ((state->colours[loc] & 1) == state->current_colour)) { + + // Pre-compute end-stops and crushes + uint8_t end_stops[4], crushes[4] = {0, 0, 0, 0}; + + // These are upper bounds, not counting walls and such. + // UP DOWN LEFT RIGHT + end_stops[0] = DANGER_MIN(al_board_size - row - 1, count); + end_stops[1] = DANGER_MIN(row, count); + end_stops[2] = DANGER_MIN(col, count); + end_stops[3] = DANGER_MIN(al_board_size - col - 1, count); + + // Now we check for caps and walls + const uint8_t cap_top = STONE_AT(state, loc) == STONE_CAPSTONE; + for (int d = 0; d < 4; d++) { + const int delta = move_deltas[d]; + const int stop = end_stops[d]; + end_stops[d] = 0; + for (int k = 1; k <= stop; k++) { + const enum STONE_VARIANT stone = STONE_AT(state, loc + k * delta); + if (stone == STONE_STANDING) { + if (cap_top) { + crushes[d] = k; + end_stops[d]++; + } + break; + } else if (stone == STONE_CAPSTONE) { + break; + } + end_stops[d]++; + } + } + /* + * For each direction, generate all possible ordered integer + * partitions of 1 ≤ num ≤ count whose number of summands is in the + * range 1 ≤ # summands ≤ min(end_stops[dir], num) -- we write + * summands as steps. + * + * We exploit the `gaps' bijection here and elsewhere between ordered + * {integer partitions of n with s summands} and {binary strings of + * length n-1 with s-1 set bits}. + */ + for (enum MOVE_DIRECTION dir = M_UP; dir <= M_RIGHT; dir++) { + const int8_t delta = move_deltas[dir]; + for (uint8_t num = 1; num <= count; num++) { + for (uint8_t steps = 1; steps <= end_stops[dir] && steps <= num; + steps++) { + uint8_t gaps = ((1 << (al_board_size - 2)) - 1) >> + (al_board_size - steps - 1); + // For 5x5 this gives 0b0000[0XXX] where steps-1 of those X's + // are 1s (starting with LSB) because 4-1=3 and 5-1=4 + do { + /* + * We skip the partition if it calls for multiple stones at + * the end with a crush, or if it would cause any stack to + * grow beyond height 15. + */ + const uint8_t no_overflow = + check_no_overflow(state, loc, delta, num, steps, gaps); + const uint8_t last_drop_check = + (num > 1) ? (gaps & (1 << (num - 2))) : 1; + const uint8_t can_and_must_crush = + crushes[dir] == steps && last_drop_check; + const uint8_t crush_check = + can_and_must_crush || crushes[dir] != steps; + if (no_overflow && crush_check) { + // Store the move + list_append(list, A_MOVE, loc, + (can_and_must_crush << 7) | gaps, + (dir << 4) | num); + } + /* + * With thanks to + * https://graphics.stanford.edu/~seander/bithacks.html#NextBitPermutation + * we have the following magic to generate the next + * permutation of steps-many set bits + */ + uint8_t t = (gaps | (gaps - 1)); + gaps = + (t + 1) | (((~t & -~t) - 1) >> (__builtin_ctz(gaps) + 1)); + } while (gaps && (gaps + 1 <= (1 << (num - 1)))); + } + } + } + } } // end of if (count) { ... } else if (material) { - // Empty square, generate placements - if (flat) { - list_prepend(list, A_PLACE, loc, STONE_FLAT, 0); - if (standing) - list_prepend(list, A_PLACE, loc, STONE_STANDING,0); - } - if (cap) - list_prepend(list, A_PLACE, loc, STONE_CAPSTONE, 0); + // Empty square, generate placements + if (flat) { + list_prepend(list, A_PLACE, loc, STONE_FLAT, 0); + if (standing) + list_prepend(list, A_PLACE, loc, STONE_STANDING, 0); + } + if (cap) + list_prepend(list, A_PLACE, loc, STONE_CAPSTONE, 0); } } } return list; } -void action_take(const action_t action) { +void action_take(tak_state_p state, const action_t action) { const int8_t loc = A_GET_LOC(action); if (A_GET_TYPE(action) == A_PLACE) { - const uint8_t black = (current_colour == C_BLACK); + const uint8_t black = (state->current_colour == C_BLACK); switch (A_GET_DATA0(action)) { - case STONE_FLAT: { - if (black) black_count--; - else white_count--; - colours[loc] = current_colour; - celldat[loc] = NUM_INC | STONE_FLAT; - break; - } - case STONE_STANDING: { - if (black) black_count--; - else white_count--; - colours[loc] = current_colour; - celldat[loc] = NUM_INC | STONE_STANDING; - break; - } - default: { - if (black) black_count &= 0x7F; - else white_count &= 0x7F; - colours[loc] = current_colour; - celldat[loc] = NUM_INC | STONE_CAPSTONE; - break; - } + case STONE_FLAT: { + if (black) + state->black_count--; + else + state->white_count--; + state->colours[loc] = state->current_colour; + state->celldat[loc] = NUM_INC | STONE_FLAT; + break; + } + case STONE_STANDING: { + if (black) + state->black_count--; + else + state->white_count--; + state->colours[loc] = state->current_colour; + state->celldat[loc] = NUM_INC | STONE_STANDING; + break; + } + default: { + if (black) + state->black_count &= 0x7F; + else + state->white_count &= 0x7F; + state->colours[loc] = state->current_colour; + state->celldat[loc] = NUM_INC | STONE_CAPSTONE; + break; + } } } else { /* - * See the discussion around line 135 for an explanation of the - * encoding. Here we are not interested in whether we crushed, it - * will work out by anyway because we overwrite the top stone - * type. See (*) later for when we do need to know. + * See the discussion around line 160 for an explanation of the encoding. + * Here we are not interested in whether we crushed, it will work out by + * anyway because we overwrite the top stone type. See (*) later for when we + * do need to know. */ const uint8_t gaps = A_GET_DATA0(action) & 0x7F, - num = A_GET_DATA1(action) & 0x0F, // unpack - dir = A_GET_DATA1(action) >> 4; + num = A_GET_DATA1(action) & 0x0F, // unpack + dir = A_GET_DATA1(action) >> 4; int8_t delta = move_deltas[dir]; // Use the Kernighan method to count the set bits int8_t steps = 1; - for (uint8_t _gaps = gaps; _gaps; steps++) _gaps &= _gaps - 1; + for (uint8_t _gaps = gaps; _gaps; steps++) + _gaps &= _gaps - 1; // Move top stone type to destination - celldat[loc+steps*delta] &= CLR_STONE; // necessary for crushing - celldat[loc+steps*delta] |= STONE_AT(loc); - celldat[loc] &= CLR_STONE; - celldat[loc] |= STONE_FLAT; // should be optimised out - - uint8_t total = 1, gap_bit = 1 << (num - 2); // it's not important - // what negative - // shifts do here, we - // don't use gap_bit - // if num < 2 + state->celldat[loc + steps * delta] &= CLR_STONE; // necessary for crushing + state->celldat[loc + steps * delta] |= STONE_AT(state, loc); + state->celldat[loc] &= CLR_STONE; + state->celldat[loc] |= STONE_FLAT; // should be optimised out + + uint8_t total = 1, gap_bit = 1 << (num - 2); // it's not important what + // negative shifts do here, we + // don't use gap_bit if num < 2 + // move stuff starting at destination for (uint8_t d = 1; d < num; d++, total++, gap_bit >>= 1) { // We took a step, move everything over so far if (gaps & gap_bit) { - colours[loc+steps*delta] <<= total; - colours[loc+steps*delta] |= colours[loc] & ((1 << total) - 1); - colours[loc] >>= total; - celldat[loc+steps*delta] += total*NUM_INC; - celldat[loc] -= total*NUM_INC; - // Reset for next step - total = 0; - steps--; + state->colours[loc + steps * delta] <<= total; + state->colours[loc + steps * delta] |= + state->colours[loc] & ((1 << total) - 1); + state->colours[loc] >>= total; + state->celldat[loc + steps * delta] += total * NUM_INC; + state->celldat[loc] -= total * NUM_INC; + // Reset for next step + total = 0; + steps--; } } // Move what remains (steps == 1 here always, so we simplify) - colours[loc+delta] <<= total; - colours[loc+delta] |= colours[loc] & ((1 << total) - 1); - colours[loc] >>= total; - celldat[loc+delta] += total*NUM_INC; - celldat[loc] -= total*NUM_INC; + state->colours[loc + delta] <<= total; + state->colours[loc + delta] |= state->colours[loc] & ((1 << total) - 1); + state->colours[loc] >>= total; + state->celldat[loc + delta] += total * NUM_INC; + state->celldat[loc] -= total * NUM_INC; } // Next ply - inline_next_ply(); + inline_next_ply(state); } -void action_undo(const action_t action) { +void action_undo(tak_state_p state, const action_t action) { // Previous ply - inline_prev_ply(); + inline_prev_ply(state); const int8_t loc = A_GET_LOC(action); if (A_GET_TYPE(action) == A_PLACE) { - const uint8_t black = (current_colour == C_BLACK); - celldat[loc] = 0; + const uint8_t black = (state->current_colour == C_BLACK); + state->celldat[loc] = 0; if (A_GET_DATA0(action) == STONE_CAPSTONE) { - if (black) black_count |= 0x80; - else white_count |= 0x80; + if (black) + state->black_count |= 0x80; + else + state->white_count |= 0x80; } else { - if (black) black_count++; - else white_count++; + if (black) + state->black_count++; + else + state->white_count++; } } else { // See action_take for comments, this is the time reversal, but // there is one caveat -- undoing a crush! (*) const uint8_t gaps = A_GET_DATA0(action) & 0x7F, - crush = A_GET_DATA0(action) & 0x80, - num = A_GET_DATA1(action) & 0x0F, - dir = A_GET_DATA1(action) >> 4; + crush = A_GET_DATA0(action) & 0x80, + num = A_GET_DATA1(action) & 0x0F, + dir = A_GET_DATA1(action) >> 4; const int8_t delta = move_deltas[dir]; int8_t steps = 1; uint8_t gap_bit = 1, total = 1; for (int8_t d = 1; d < num; d++, total++, gap_bit <<= 1) { if (gaps & gap_bit) { - colours[loc] <<= total; - colours[loc] |= colours[loc+steps*delta] & ((1 << total) - 1); - colours[loc+steps*delta] >>= total; - celldat[loc] += total*NUM_INC; - celldat[loc+steps*delta] -= total*NUM_INC; - total = 0; - steps++; + state->colours[loc] <<= total; + state->colours[loc] |= + state->colours[loc + steps * delta] & ((1 << total) - 1); + state->colours[loc + steps * delta] >>= total; + state->celldat[loc] += total * NUM_INC; + state->celldat[loc + steps * delta] -= total * NUM_INC; + total = 0; + steps++; } } - colours[loc] <<= total; - colours[loc] |= colours[loc+steps*delta] & ((1 << total) - 1); - colours[loc+steps*delta] >>= total; + state->colours[loc] <<= total; + state->colours[loc] |= + state->colours[loc + steps * delta] & ((1 << total) - 1); + state->colours[loc + steps * delta] >>= total; - celldat[loc] += total*NUM_INC; + state->celldat[loc] += total * NUM_INC; // celldat[loc] &= CLR_STONE; is not necessary, as STONE_FLAT == 0 - celldat[loc] |= STONE_AT(loc+steps*delta); - celldat[loc+steps*delta] -= total*NUM_INC; - celldat[loc+steps*delta] &= CLR_STONE; + state->celldat[loc] |= STONE_AT(state, loc + steps * delta); + state->celldat[loc + steps * delta] -= total * NUM_INC; + state->celldat[loc + steps * delta] &= CLR_STONE; if (crush) { - celldat[loc+steps*delta] |= STONE_STANDING; + state->celldat[loc + steps * delta] |= STONE_STANDING; } else { - celldat[loc+steps*delta] |= STONE_FLAT; // should be optimised out + state->celldat[loc + steps * delta] |= + STONE_FLAT; // should be optimised out } } } -void action_to_ptn(const action_t action, char* out_ptn) { +void action_to_ptn(const action_t action, char *out_ptn) { const int8_t loc = A_GET_LOC(action); if (A_GET_TYPE(action) == A_PLACE) { - generate_place(loc, A_GET_DATA0(action), out_ptn); + generate_place(al_board_size, loc, A_GET_DATA0(action), out_ptn); } else { const uint8_t gaps = A_GET_DATA0(action) & 0x7F, - num = A_GET_DATA1(action) & 0x0F, // unpack - dir = A_GET_DATA1(action) >> 4; + num = A_GET_DATA1(action) & 0x0F, // unpack + dir = A_GET_DATA1(action) >> 4; - uint8_t drops[board_size]; // we only ever need board_size-1 in - // drops actually, the last spot is to - // skip a bounds check at (**) + uint8_t drops[al_board_size]; // we only ever need al_board_size-1 in drops + // actually, the last spot is to skip a bounds + // check at (**) uint8_t mask = 1, steps = 0; // Translate to a drop sequence - drops[0] = 1; mask = 1; + drops[0] = 1; + mask = 1; for (uint8_t d = 1; d < num; d++) { if (gaps & mask) { - steps++; - drops[steps] = 1; // (**) no bounds check + steps++; + drops[steps] = 1; // (**) no bounds check } else { - drops[steps] += 1; + drops[steps] += 1; } mask <<= 1; } - generate_move(loc, dir, steps+1, drops, out_ptn); + generate_move(al_board_size, loc, dir, steps + 1, drops, out_ptn); } } @@ -382,10 +406,9 @@ void action_to_ptn(const action_t action, char* out_ptn) { // Helper method implementations // =================================================================== -static inline void -list_append(action_list_t *list, const enum A_TYPE type, - const int8_t loc, const uint8_t data0, - const uint8_t data1) { +static inline void list_append(action_list_t *list, const enum A_TYPE type, + const int8_t loc, const uint8_t data0, + const uint8_t data1) { action_node_t *new = malloc(sizeof(action_node_t)); // TODO: trap errno @@ -403,10 +426,9 @@ list_append(action_list_t *list, const enum A_TYPE type, list->length++; } -static inline void -list_prepend(action_list_t *list, const enum A_TYPE type, - const int8_t loc, const uint8_t data0, - const uint8_t data1) { +static inline void list_prepend(action_list_t *list, const enum A_TYPE type, + const int8_t loc, const uint8_t data0, + const uint8_t data1) { action_node_t *new = malloc(sizeof(action_list_t)); // TODO: trap errno @@ -421,24 +443,46 @@ list_prepend(action_list_t *list, const enum A_TYPE type, list->length++; } -static inline void -inline_next_ply(void) { - ply++; - if (ply == 2) { - current_colour = C_WHITE; +static inline void inline_next_ply(tak_state_p state) { + state->ply++; + if (state->ply == 2) { + state->current_colour = C_WHITE; } else { - if (current_colour == C_BLACK) current_colour = C_WHITE; - else current_colour = C_BLACK; + if (state->current_colour == C_BLACK) + state->current_colour = C_WHITE; + else + state->current_colour = C_BLACK; } } -static inline void -inline_prev_ply(void) { - if (ply>0) ply--; - if (ply == 1) { - current_colour = C_WHITE; +static inline void inline_prev_ply(tak_state_p state) { + if (state->ply > 0) + state->ply--; + if (state->ply == 1) { + state->current_colour = C_WHITE; } else { - if (current_colour == C_BLACK) current_colour = C_WHITE; - else current_colour = C_BLACK; + if (state->current_colour == C_BLACK) + state->current_colour = C_WHITE; + else + state->current_colour = C_BLACK; + } +} + +static inline uint8_t check_no_overflow(tak_state_p state, const uint8_t loc, + const int8_t delta, const uint8_t num, + const uint8_t steps, + const uint8_t gaps) { + uint8_t total = 1, gap_bit = 1 << (num - 2), step = steps; + for (uint8_t d = 1; d < num; d++, total++, gap_bit >>= 1) { + if (gaps & gap_bit) { + if (COUNT_AT(state, loc + step * delta) + total > 15) + return 0; + step--; + total = 0; + } } + if (COUNT_AT(state, loc + delta) + total > 15) + return 0; + + return 1; } |
