daniel156161
c646392b84
- Preserve snake customizations across database migrations and merges. - Lazily load optional storage backends for SQLite maintenance scripts. - Match Apex territory and nearest-food tie-breaking semantics. - Resolve duel occupancy after simultaneous movement and food growth. - Recompute simulated head-to-head danger after body growth. - Add regression coverage and declare the aiofiles dependency.
291 lines
9.7 KiB
Python
291 lines
9.7 KiB
Python
"""Deadline-aware simultaneous duel search using compact tuple bodies and bitboards."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from time import perf_counter
|
|
from typing import Iterable
|
|
|
|
from snakes.bitboard import BitBoard
|
|
|
|
Body = tuple[int, ...]
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class DuelState:
|
|
my_body: Body
|
|
enemy_body: Body
|
|
food_bits: int
|
|
my_health: int
|
|
enemy_health: int
|
|
previous_hazard_bits: int
|
|
|
|
class BitboardDuelSearch:
|
|
"""Iterative-deepening paranoid minimax for a two-snake game.
|
|
|
|
The public API still accepts Battlesnake body dictionaries. Search nodes use
|
|
flat cell indices, immutable tuples, and integer masks to avoid allocation of
|
|
coordinate dictionaries and sets in the hot path.
|
|
"""
|
|
|
|
WIN = 100_000.0
|
|
LOSS = -100_000.0
|
|
|
|
def __init__(
|
|
self,
|
|
board: BitBoard,
|
|
food: Iterable[tuple[int, int]],
|
|
hazards: Iterable[tuple[int, int]],
|
|
hazard_count: dict[tuple[int, int], int],
|
|
hazard_damage: int,
|
|
deadline: float | None,
|
|
) -> None:
|
|
self.board = board
|
|
self.deadline = deadline
|
|
self.hazard_damage = hazard_damage
|
|
self.food_bits = board.set_to_bits(set(food))
|
|
self.hazard_bits = board.set_to_bits(set(hazards))
|
|
self.hazard_stacks = {
|
|
board.idx(x, y): count for (x, y), count in hazard_count.items()
|
|
}
|
|
self.transposition: dict[tuple[DuelState, int], tuple[float, str]] = {}
|
|
self.killer_moves: dict[int, int] = {}
|
|
self.history: dict[int, int] = {}
|
|
self.nodes = 0
|
|
self.cache_hits = 0
|
|
|
|
def body_from_dicts(self, body: list[dict]) -> Body:
|
|
return tuple(self.board.idx(seg["x"], seg["y"]) for seg in body)
|
|
|
|
def search(
|
|
self,
|
|
my_body: list[dict],
|
|
enemy_body: list[dict],
|
|
my_health: int,
|
|
enemy_health: int,
|
|
max_depth: int,
|
|
previous_hazards: Iterable[tuple[int, int]],
|
|
) -> tuple[float, int]:
|
|
state = DuelState(
|
|
my_body=self.body_from_dicts(my_body),
|
|
enemy_body=self.body_from_dicts(enemy_body),
|
|
food_bits=self.food_bits,
|
|
my_health=my_health,
|
|
enemy_health=enemy_health,
|
|
previous_hazard_bits=self.board.set_to_bits(set(previous_hazards)),
|
|
)
|
|
result = self._evaluate(state)
|
|
completed_depth = 0
|
|
|
|
for depth in range(1, max_depth + 1):
|
|
if self._out_of_time(5.0):
|
|
break
|
|
value, completed = self._search(state, depth, -float("inf"), float("inf"))
|
|
if not completed:
|
|
break
|
|
result = value
|
|
completed_depth = depth
|
|
|
|
return result, completed_depth
|
|
|
|
def search_depth(
|
|
self,
|
|
my_body: list[dict],
|
|
enemy_body: list[dict],
|
|
my_health: int,
|
|
enemy_health: int,
|
|
depth: int,
|
|
previous_hazards: Iterable[tuple[int, int]],
|
|
) -> float:
|
|
state = DuelState(
|
|
my_body=self.body_from_dicts(my_body),
|
|
enemy_body=self.body_from_dicts(enemy_body),
|
|
food_bits=self.food_bits,
|
|
my_health=my_health,
|
|
enemy_health=enemy_health,
|
|
previous_hazard_bits=self.board.set_to_bits(set(previous_hazards)),
|
|
)
|
|
value, _ = self._search(state, depth, -float("inf"), float("inf"))
|
|
return value
|
|
|
|
def _search(self, state: DuelState, depth: int, alpha: float, beta: float) -> tuple[float, bool]:
|
|
self.nodes += 1
|
|
if self._out_of_time():
|
|
return self._evaluate(state), False
|
|
if depth <= 0:
|
|
return self._evaluate(state), True
|
|
|
|
cache_key = (state, depth)
|
|
original_alpha, original_beta = alpha, beta
|
|
cached = self.transposition.get(cache_key)
|
|
if cached is not None:
|
|
self.cache_hits += 1
|
|
cached_value, bound = cached
|
|
if bound == "exact":
|
|
return cached_value, True
|
|
if bound == "lower":
|
|
alpha = max(alpha, cached_value)
|
|
else:
|
|
beta = min(beta, cached_value)
|
|
if alpha >= beta:
|
|
return cached_value, True
|
|
|
|
my_moves = self._candidate_targets(state.my_body)
|
|
enemy_moves = self._candidate_targets(state.enemy_body)
|
|
if not my_moves:
|
|
return self.LOSS - depth, True
|
|
if not enemy_moves:
|
|
return self.WIN + depth, True
|
|
|
|
my_moves = self._ordered_moves(my_moves, state, depth, True)
|
|
enemy_moves = self._ordered_moves(enemy_moves, state, depth, False)
|
|
best = -float("inf")
|
|
|
|
for my_target in my_moves:
|
|
worst = float("inf")
|
|
for enemy_target in enemy_moves:
|
|
if self._out_of_time():
|
|
return (best if best != -float("inf") else self._evaluate(state)), False
|
|
child, terminal = self._advance(state, my_target, enemy_target)
|
|
if terminal is not None:
|
|
value = terminal
|
|
completed = True
|
|
else:
|
|
value, completed = self._search(child, depth - 1, alpha, beta)
|
|
if not completed:
|
|
return (best if best != -float("inf") else value), False
|
|
worst = min(worst, value)
|
|
if worst <= alpha:
|
|
self.killer_moves[depth] = my_target
|
|
self.history[my_target] = self.history.get(my_target, 0) + depth * depth
|
|
break
|
|
|
|
best = max(best, worst)
|
|
alpha = max(alpha, best)
|
|
if alpha >= beta:
|
|
break
|
|
|
|
if best <= original_alpha:
|
|
bound = "upper"
|
|
elif best >= original_beta:
|
|
bound = "lower"
|
|
else:
|
|
bound = "exact"
|
|
self.transposition[cache_key] = (best, bound)
|
|
return best, True
|
|
|
|
def _advance(self, state: DuelState, my_target: int, enemy_target: int) -> tuple[DuelState, float | None]:
|
|
my_ate = bool((1 << my_target) & state.food_bits)
|
|
enemy_ate = bool((1 << enemy_target) & state.food_bits)
|
|
my_body = self._advance_body(state.my_body, my_target, my_ate)
|
|
enemy_body = self._advance_body(state.enemy_body, enemy_target, enemy_ate)
|
|
|
|
my_dead = my_target in my_body[1:] or my_target in enemy_body[1:]
|
|
enemy_dead = enemy_target in enemy_body[1:] or enemy_target in my_body[1:]
|
|
|
|
if my_target == enemy_target:
|
|
if len(my_body) <= len(enemy_body):
|
|
my_dead = True
|
|
if len(enemy_body) <= len(my_body):
|
|
enemy_dead = True
|
|
|
|
my_health = 100 if my_ate else state.my_health - 1
|
|
enemy_health = 100 if enemy_ate else state.enemy_health - 1
|
|
if not my_ate:
|
|
my_health -= self._hazard_cost(my_target, state.previous_hazard_bits)
|
|
if not enemy_ate:
|
|
enemy_health -= self._hazard_cost(enemy_target, state.previous_hazard_bits)
|
|
my_dead = my_dead or my_health <= 0
|
|
enemy_dead = enemy_dead or enemy_health <= 0
|
|
|
|
if my_dead and enemy_dead:
|
|
return state, -500.0
|
|
if my_dead:
|
|
return state, self.LOSS
|
|
if enemy_dead:
|
|
return state, self.WIN
|
|
|
|
eaten_bits = 0
|
|
if my_ate:
|
|
eaten_bits |= 1 << my_target
|
|
if enemy_ate:
|
|
eaten_bits |= 1 << enemy_target
|
|
child = DuelState(
|
|
my_body=my_body,
|
|
enemy_body=enemy_body,
|
|
food_bits=state.food_bits & ~eaten_bits,
|
|
my_health=my_health,
|
|
enemy_health=enemy_health,
|
|
previous_hazard_bits=self.hazard_bits,
|
|
)
|
|
return child, None
|
|
|
|
def _candidate_targets(self, body: Body) -> list[int]:
|
|
"""Return in-bounds targets; `_advance` resolves simultaneous collisions.
|
|
|
|
Delaying occupancy checks until both targets and food growth are known is
|
|
essential: whether either tail vacates depends on that snake eating.
|
|
"""
|
|
return list(self._iter_bits(self.board.neighbors_of(body[0])))
|
|
|
|
def _ordered_moves(self, moves: list[int], state: DuelState, depth: int, mine: bool) -> list[int]:
|
|
body = state.my_body if mine else state.enemy_body
|
|
other = state.enemy_body if mine else state.my_body
|
|
killer = self.killer_moves.get(depth)
|
|
center_x = (self.board.width - 1) / 2.0
|
|
center_y = (self.board.height - 1) / 2.0
|
|
|
|
def score(target: int) -> tuple[float, int]:
|
|
x, y = self.board.coord(target)
|
|
food_bonus = 200.0 if (1 << target) & state.food_bits else 0.0
|
|
space = self.board.flood_count(target, (self._body_bits(body[1:]) | self._body_bits(other[1:])) & ~(1 << target))
|
|
center = -(abs(x - center_x) + abs(y - center_y))
|
|
killer_bonus = 10_000.0 if target == killer else 0.0
|
|
return killer_bonus + self.history.get(target, 0) + food_bonus + space * 2.0 + center, -target
|
|
|
|
# Our strongest-looking moves first; enemy ordering uses the same quality
|
|
# estimate because dangerous enemy replies tend to gain space and food.
|
|
return sorted(moves, key=score, reverse=True)
|
|
|
|
def _evaluate(self, state: DuelState) -> float:
|
|
my_blocked = self._body_bits(state.my_body[1:]) | self._body_bits(state.enemy_body[1:])
|
|
my_space = self.board.flood_count(state.my_body[0], my_blocked)
|
|
enemy_space = self.board.flood_count(state.enemy_body[0], my_blocked)
|
|
my_liberties = self.board.open_neighbor_count(state.my_body[0], my_blocked)
|
|
enemy_liberties = self.board.open_neighbor_count(state.enemy_body[0], my_blocked)
|
|
length_score = (len(state.my_body) - len(state.enemy_body)) * 18.0
|
|
health_score = (state.my_health - state.enemy_health) * 0.15
|
|
return (my_space - enemy_space) * 2.0 + (my_liberties - enemy_liberties) * 12.0 + length_score + health_score
|
|
|
|
def _hazard_cost(self, target: int, previous_hazard_bits: int) -> int:
|
|
bit = 1 << target
|
|
if not (bit & self.hazard_bits & previous_hazard_bits):
|
|
return 0
|
|
return self.hazard_damage * self.hazard_stacks.get(target, 1)
|
|
|
|
@staticmethod
|
|
def _advance_body(body: Body, target: int, ate: bool) -> Body:
|
|
return (target,) + body if ate else (target,) + body[:-1]
|
|
|
|
@staticmethod
|
|
def _tail_stacked(body: Body) -> bool:
|
|
return len(body) >= 2 and body[-1] == body[-2]
|
|
|
|
@staticmethod
|
|
def _body_bits(body: Body) -> int:
|
|
bits = 0
|
|
for cell in body:
|
|
bits |= 1 << cell
|
|
return bits
|
|
|
|
@staticmethod
|
|
def _iter_bits(bits: int):
|
|
while bits:
|
|
bit = bits & -bits
|
|
yield bit.bit_length() - 1
|
|
bits ^= bit
|
|
|
|
def _out_of_time(self, reserve_ms: float = 0.0) -> bool:
|
|
if self.deadline is None:
|
|
return False
|
|
return perf_counter() + reserve_ms / 1000.0 >= self.deadline
|