Spaces:
Running
Running
File size: 13,715 Bytes
375a1cf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 |
from contextlib import closing
from io import StringIO
from os import path
from typing import List, Optional
import numpy as np
from gym import Env, logger, spaces, utils
from gym.envs.toy_text.utils import categorical_sample
from gym.error import DependencyNotInstalled
LEFT = 0
DOWN = 1
RIGHT = 2
UP = 3
MAPS = {
"4x4": ["SFFF", "FHFH", "FFFH", "HFFG"],
"8x8": [
"SFFFFFFF",
"FFFFFFFF",
"FFFHFFFF",
"FFFFFHFF",
"FFFHFFFF",
"FHHFFFHF",
"FHFFHFHF",
"FFFHFFFG",
],
}
# DFS to check that it's a valid path.
def is_valid(board: List[List[str]], max_size: int) -> bool:
frontier, discovered = [], set()
frontier.append((0, 0))
while frontier:
r, c = frontier.pop()
if not (r, c) in discovered:
discovered.add((r, c))
directions = [(1, 0), (0, 1), (-1, 0), (0, -1)]
for x, y in directions:
r_new = r + x
c_new = c + y
if r_new < 0 or r_new >= max_size or c_new < 0 or c_new >= max_size:
continue
if board[r_new][c_new] == "G":
return True
if board[r_new][c_new] != "H":
frontier.append((r_new, c_new))
return False
def generate_random_map(size: int = 8, p: float = 0.8) -> List[str]:
"""Generates a random valid map (one that has a path from start to goal)
Args:
size: size of each side of the grid
p: probability that a tile is frozen
Returns:
A random valid map
"""
valid = False
board = [] # initialize to make pyright happy
while not valid:
p = min(1, p)
board = np.random.choice(["F", "H"], (size, size), p=[p, 1 - p])
board[0][0] = "S"
board[-1][-1] = "G"
valid = is_valid(board, size)
return ["".join(x) for x in board]
class FrozenLakeEnv(Env):
"""
Frozen lake involves crossing a frozen lake from Start(S) to Goal(G) without falling into any Holes(H)
by walking over the Frozen(F) lake.
The agent may not always move in the intended direction due to the slippery nature of the frozen lake.
### Action Space
The agent takes a 1-element vector for actions.
The action space is `(dir)`, where `dir` decides direction to move in which can be:
- 0: LEFT
- 1: DOWN
- 2: RIGHT
- 3: UP
### Observation Space
The observation is a value representing the agent's current position as
current_row * nrows + current_col (where both the row and col start at 0).
For example, the goal position in the 4x4 map can be calculated as follows: 3 * 4 + 3 = 15.
The number of possible observations is dependent on the size of the map.
For example, the 4x4 map has 16 possible observations.
### Rewards
Reward schedule:
- Reach goal(G): +1
- Reach hole(H): 0
- Reach frozen(F): 0
### Arguments
```
gym.make('FrozenLake-v1', desc=None, map_name="4x4", is_slippery=True)
```
`desc`: Used to specify custom map for frozen lake. For example,
desc=["SFFF", "FHFH", "FFFH", "HFFG"].
A random generated map can be specified by calling the function `generate_random_map`. For example,
```
from gym.envs.toy_text.frozen_lake import generate_random_map
gym.make('FrozenLake-v1', desc=generate_random_map(size=8))
```
`map_name`: ID to use any of the preloaded maps.
"4x4":[
"SFFF",
"FHFH",
"FFFH",
"HFFG"
]
"8x8": [
"SFFFFFFF",
"FFFFFFFF",
"FFFHFFFF",
"FFFFFHFF",
"FFFHFFFF",
"FHHFFFHF",
"FHFFHFHF",
"FFFHFFFG",
]
`is_slippery`: True/False. If True will move in intended direction with
probability of 1/3 else will move in either perpendicular direction with
equal probability of 1/3 in both directions.
For example, if action is left and is_slippery is True, then:
- P(move left)=1/3
- P(move up)=1/3
- P(move down)=1/3
### Version History
* v1: Bug fixes to rewards
* v0: Initial versions release (1.0.0)
"""
metadata = {
"render_modes": ["human", "ansi", "rgb_array"],
"render_fps": 4,
}
def __init__(
self,
render_mode: Optional[str] = None,
desc=None,
map_name="4x4",
is_slippery=True,
):
if desc is None and map_name is None:
desc = generate_random_map()
elif desc is None:
desc = MAPS[map_name]
self.desc = desc = np.asarray(desc, dtype="c")
self.nrow, self.ncol = nrow, ncol = desc.shape
self.reward_range = (0, 1)
nA = 4
nS = nrow * ncol
self.initial_state_distrib = np.array(desc == b"S").astype("float64").ravel()
self.initial_state_distrib /= self.initial_state_distrib.sum()
self.P = {s: {a: [] for a in range(nA)} for s in range(nS)}
def to_s(row, col):
return row * ncol + col
def inc(row, col, a):
if a == LEFT:
col = max(col - 1, 0)
elif a == DOWN:
row = min(row + 1, nrow - 1)
elif a == RIGHT:
col = min(col + 1, ncol - 1)
elif a == UP:
row = max(row - 1, 0)
return (row, col)
def update_probability_matrix(row, col, action):
newrow, newcol = inc(row, col, action)
newstate = to_s(newrow, newcol)
newletter = desc[newrow, newcol]
terminated = bytes(newletter) in b"GH"
reward = float(newletter == b"G")
return newstate, reward, terminated
for row in range(nrow):
for col in range(ncol):
s = to_s(row, col)
for a in range(4):
li = self.P[s][a]
letter = desc[row, col]
if letter in b"GH":
li.append((1.0, s, 0, True))
else:
if is_slippery:
for b in [(a - 1) % 4, a, (a + 1) % 4]:
li.append(
(1.0 / 3.0, *update_probability_matrix(row, col, b))
)
else:
li.append((1.0, *update_probability_matrix(row, col, a)))
self.observation_space = spaces.Discrete(nS)
self.action_space = spaces.Discrete(nA)
self.render_mode = render_mode
# pygame utils
self.window_size = (min(64 * ncol, 512), min(64 * nrow, 512))
self.cell_size = (
self.window_size[0] // self.ncol,
self.window_size[1] // self.nrow,
)
self.window_surface = None
self.clock = None
self.hole_img = None
self.cracked_hole_img = None
self.ice_img = None
self.elf_images = None
self.goal_img = None
self.start_img = None
def step(self, a):
transitions = self.P[self.s][a]
i = categorical_sample([t[0] for t in transitions], self.np_random)
p, s, r, t = transitions[i]
self.s = s
self.lastaction = a
if self.render_mode == "human":
self.render()
return (int(s), r, t, False, {"prob": p})
def reset(
self,
*,
seed: Optional[int] = None,
options: Optional[dict] = None,
):
super().reset(seed=seed)
self.s = categorical_sample(self.initial_state_distrib, self.np_random)
self.lastaction = None
if self.render_mode == "human":
self.render()
return int(self.s), {"prob": 1}
def render(self):
if self.render_mode is None:
logger.warn(
"You are calling render method without specifying any render mode. "
"You can specify the render_mode at initialization, "
f'e.g. gym("{self.spec.id}", render_mode="rgb_array")'
)
elif self.render_mode == "ansi":
return self._render_text()
else: # self.render_mode in {"human", "rgb_array"}:
return self._render_gui(self.render_mode)
def _render_gui(self, mode):
try:
import pygame
except ImportError:
raise DependencyNotInstalled(
"pygame is not installed, run `pip install gym[toy_text]`"
)
if self.window_surface is None:
pygame.init()
if mode == "human":
pygame.display.init()
pygame.display.set_caption("Frozen Lake")
self.window_surface = pygame.display.set_mode(self.window_size)
elif mode == "rgb_array":
self.window_surface = pygame.Surface(self.window_size)
assert (
self.window_surface is not None
), "Something went wrong with pygame. This should never happen."
if self.clock is None:
self.clock = pygame.time.Clock()
if self.hole_img is None:
file_name = path.join(path.dirname(__file__), "img/hole.png")
self.hole_img = pygame.transform.scale(
pygame.image.load(file_name), self.cell_size
)
if self.cracked_hole_img is None:
file_name = path.join(path.dirname(__file__), "img/cracked_hole.png")
self.cracked_hole_img = pygame.transform.scale(
pygame.image.load(file_name), self.cell_size
)
if self.ice_img is None:
file_name = path.join(path.dirname(__file__), "img/ice.png")
self.ice_img = pygame.transform.scale(
pygame.image.load(file_name), self.cell_size
)
if self.goal_img is None:
file_name = path.join(path.dirname(__file__), "img/goal.png")
self.goal_img = pygame.transform.scale(
pygame.image.load(file_name), self.cell_size
)
if self.start_img is None:
file_name = path.join(path.dirname(__file__), "img/stool.png")
self.start_img = pygame.transform.scale(
pygame.image.load(file_name), self.cell_size
)
if self.elf_images is None:
elfs = [
path.join(path.dirname(__file__), "img/elf_left.png"),
path.join(path.dirname(__file__), "img/elf_down.png"),
path.join(path.dirname(__file__), "img/elf_right.png"),
path.join(path.dirname(__file__), "img/elf_up.png"),
]
self.elf_images = [
pygame.transform.scale(pygame.image.load(f_name), self.cell_size)
for f_name in elfs
]
desc = self.desc.tolist()
assert isinstance(desc, list), f"desc should be a list or an array, got {desc}"
for y in range(self.nrow):
for x in range(self.ncol):
pos = (x * self.cell_size[0], y * self.cell_size[1])
rect = (*pos, *self.cell_size)
self.window_surface.blit(self.ice_img, pos)
if desc[y][x] == b"H":
self.window_surface.blit(self.hole_img, pos)
elif desc[y][x] == b"G":
self.window_surface.blit(self.goal_img, pos)
elif desc[y][x] == b"S":
self.window_surface.blit(self.start_img, pos)
pygame.draw.rect(self.window_surface, (180, 200, 230), rect, 1)
# paint the elf
bot_row, bot_col = self.s // self.ncol, self.s % self.ncol
cell_rect = (bot_col * self.cell_size[0], bot_row * self.cell_size[1])
last_action = self.lastaction if self.lastaction is not None else 1
elf_img = self.elf_images[last_action]
if desc[bot_row][bot_col] == b"H":
self.window_surface.blit(self.cracked_hole_img, cell_rect)
else:
self.window_surface.blit(elf_img, cell_rect)
if mode == "human":
pygame.event.pump()
pygame.display.update()
self.clock.tick(self.metadata["render_fps"])
elif mode == "rgb_array":
return np.transpose(
np.array(pygame.surfarray.pixels3d(self.window_surface)), axes=(1, 0, 2)
)
@staticmethod
def _center_small_rect(big_rect, small_dims):
offset_w = (big_rect[2] - small_dims[0]) / 2
offset_h = (big_rect[3] - small_dims[1]) / 2
return (
big_rect[0] + offset_w,
big_rect[1] + offset_h,
)
def _render_text(self):
desc = self.desc.tolist()
outfile = StringIO()
row, col = self.s // self.ncol, self.s % self.ncol
desc = [[c.decode("utf-8") for c in line] for line in desc]
desc[row][col] = utils.colorize(desc[row][col], "red", highlight=True)
if self.lastaction is not None:
outfile.write(f" ({['Left', 'Down', 'Right', 'Up'][self.lastaction]})\n")
else:
outfile.write("\n")
outfile.write("\n".join("".join(line) for line in desc) + "\n")
with closing(outfile):
return outfile.getvalue()
def close(self):
if self.window_surface is not None:
import pygame
pygame.display.quit()
pygame.quit()
# Elf and stool from https://franuka.itch.io/rpg-snow-tileset
# All other assets by Mel Tillery http://www.cyaneus.com/
|