Files
Gymnasium/gymnasium/envs/toy_text/blackjack.py

311 lines
10 KiB
Python
Raw Normal View History

import os
from typing import Optional
import numpy as np
Seeding update (#2422) * Ditch most of the seeding.py and replace np_random with the numpy default_rng. Let's see if tests pass * Updated a bunch of RNG calls from the RandomState API to Generator API * black; didn't expect that, did ya? * Undo a typo * blaaack * More typo fixes * Fixed setting/getting state in multidiscrete spaces * Fix typo, fix a test to work with the new sampling * Correctly (?) pass the randomly generated seed if np_random is called with None as seed * Convert the Discrete sample to a python int (as opposed to np.int64) * Remove some redundant imports * First version of the compatibility layer for old-style RNG. Mainly to trigger tests. * Removed redundant f-strings * Style fixes, removing unused imports * Try to make tests pass by removing atari from the dockerfile * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * First attempt at deprecating `env.seed` and supporting `env.reset(seed=seed)` instead. Tests should hopefully pass but throw up a million warnings. * black; didn't expect that, didya? * Rename the reset parameter in VecEnvs back to `seed` * Updated tests to use the new seeding method * Removed a bunch of old `seed` calls. Fixed a bug in AsyncVectorEnv * Stop Discrete envs from doing part of the setup (and using the randomness) in init (as opposed to reset) * Add explicit seed to wrappers reset * Remove an accidental return * Re-add some legacy functions with a warning. * Use deprecation instead of regular warnings for the newly deprecated methods/functions
2021-12-08 22:14:15 +01:00
2022-09-08 10:10:07 +01:00
import gymnasium
from gymnasium import spaces
from gymnasium.error import DependencyNotInstalled
2016-05-10 17:05:47 +02:00
def cmp(a, b):
return float(a > b) - float(a < b)
2016-05-10 17:05:47 +02:00
# 1 = Ace, 2-10 = Number cards, Jack/Queen/King = 10
deck = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 10, 10, 10]
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
def draw_card(np_random):
return int(np_random.choice(deck))
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
def draw_hand(np_random):
return [draw_card(np_random), draw_card(np_random)]
def usable_ace(hand): # Does this hand have a usable ace?
return 1 in hand and sum(hand) + 10 <= 21
def sum_hand(hand): # Return current hand total
if usable_ace(hand):
return sum(hand) + 10
return sum(hand)
def is_bust(hand): # Is this hand a bust?
return sum_hand(hand) > 21
def score(hand): # What is the score of this hand (0 if bust)
return 0 if is_bust(hand) else sum_hand(hand)
def is_natural(hand): # Is this hand a natural blackjack?
return sorted(hand) == [1, 10]
2022-09-08 10:10:07 +01:00
class BlackjackEnv(gymnasium.Env):
"""
Blackjack is a card game where the goal is to beat the dealer by obtaining cards
that sum to closer to 21 (without going over 21) than the dealers cards.
### Description
Card Values:
- Face cards (Jack, Queen, King) have a point value of 10.
- Aces can either count as 11 (called a 'usable ace') or 1.
- Numerical cards (2-9) have a value equal to their number.
This game is played with an infinite deck (or with replacement).
The game starts with the dealer having one face up and one face down card,
while the player has two face up cards.
The player can request additional cards (hit, action=1) until they decide to stop (stick, action=0)
or exceed 21 (bust, immediate loss).
After the player sticks, the dealer reveals their facedown card, and draws
until their sum is 17 or greater. If the dealer goes bust, the player wins.
If neither the player nor the dealer busts, the outcome (win, lose, draw) is
decided by whose sum is closer to 21.
### Action Space
There are two actions: stick (0), and hit (1).
### Observation Space
The observation consists of a 3-tuple containing: the player's current sum,
the value of the dealer's one showing card (1-10 where 1 is ace),
and whether the player holds a usable ace (0 or 1).
This environment corresponds to the version of the blackjack problem
described in Example 5.1 in Reinforcement Learning: An Introduction
by Sutton and Barto (http://incompleteideas.net/book/the-book-2nd.html).
### Rewards
- win game: +1
- lose game: -1
- draw game: 0
- win game with natural blackjack:
+1.5 (if <a href="#nat">natural</a> is True)
+1 (if <a href="#nat">natural</a> is False)
### Arguments
```
2022-09-08 10:10:07 +01:00
gymnasium.make('Blackjack-v1', natural=False, sab=False)
```
<a id="nat">`natural=False`</a>: Whether to give an additional reward for
starting with a natural blackjack, i.e. starting with an ace and ten (sum is 21).
<a id="sab">`sab=False`</a>: Whether to follow the exact rules outlined in the book by
Sutton and Barto. If `sab` is `True`, the keyword argument `natural` will be ignored.
If the player achieves a natural blackjack and the dealer does not, the player
will win (i.e. get a reward of +1). The reverse rule does not apply.
If both the player and the dealer get a natural, it will be a draw (i.e. reward 0).
### Version History
* v0: Initial versions release (1.0.0)
"""
2021-07-29 02:26:34 +02:00
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
metadata = {
"render_modes": ["human", "rgb_array"],
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
"render_fps": 4,
}
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
def __init__(self, render_mode: Optional[str] = None, natural=False, sab=False):
self.action_space = spaces.Discrete(2)
2021-07-29 15:39:42 -04:00
self.observation_space = spaces.Tuple(
(spaces.Discrete(32), spaces.Discrete(11), spaces.Discrete(2))
)
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
# Flag to payout 1.5 on a "natural" blackjack win, like casino rules
# Ref: http://www.bicyclecards.com/how-to-play/blackjack/
self.natural = natural
# Flag for full agreement with the (Sutton and Barto, 2018) definition. Overrides self.natural
self.sab = sab
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
self.render_mode = render_mode
def step(self, action):
2016-06-16 00:20:22 -07:00
assert self.action_space.contains(action)
if action: # hit: add a card to players hand and return
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
self.player.append(draw_card(self.np_random))
if is_bust(self.player):
terminated = True
2021-07-29 02:26:34 +02:00
reward = -1.0
else:
terminated = False
2021-07-29 02:26:34 +02:00
reward = 0.0
else: # stick: play out the dealers hand, and score
terminated = True
while sum_hand(self.dealer) < 17:
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
self.dealer.append(draw_card(self.np_random))
reward = cmp(score(self.player), score(self.dealer))
if self.sab and is_natural(self.player) and not is_natural(self.dealer):
# Player automatically wins. Rules consistent with S&B
reward = 1.0
elif (
not self.sab
and self.natural
and is_natural(self.player)
and reward == 1.0
):
# Natural gives extra points, but doesn't autowin. Legacy implementation
reward = 1.5
if self.render_mode == "human":
self.render()
return self._get_obs(), reward, terminated, False, {}
def _get_obs(self):
return (sum_hand(self.player), self.dealer[0], usable_ace(self.player))
def reset(
self,
seed: Optional[int] = None,
options: Optional[dict] = None,
):
Seeding update (#2422) * Ditch most of the seeding.py and replace np_random with the numpy default_rng. Let's see if tests pass * Updated a bunch of RNG calls from the RandomState API to Generator API * black; didn't expect that, did ya? * Undo a typo * blaaack * More typo fixes * Fixed setting/getting state in multidiscrete spaces * Fix typo, fix a test to work with the new sampling * Correctly (?) pass the randomly generated seed if np_random is called with None as seed * Convert the Discrete sample to a python int (as opposed to np.int64) * Remove some redundant imports * First version of the compatibility layer for old-style RNG. Mainly to trigger tests. * Removed redundant f-strings * Style fixes, removing unused imports * Try to make tests pass by removing atari from the dockerfile * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * First attempt at deprecating `env.seed` and supporting `env.reset(seed=seed)` instead. Tests should hopefully pass but throw up a million warnings. * black; didn't expect that, didya? * Rename the reset parameter in VecEnvs back to `seed` * Updated tests to use the new seeding method * Removed a bunch of old `seed` calls. Fixed a bug in AsyncVectorEnv * Stop Discrete envs from doing part of the setup (and using the randomness) in init (as opposed to reset) * Add explicit seed to wrappers reset * Remove an accidental return * Re-add some legacy functions with a warning. * Use deprecation instead of regular warnings for the newly deprecated methods/functions
2021-12-08 22:14:15 +01:00
super().reset(seed=seed)
[WIP] add support for seeding environments (#135) * Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
2016-05-29 09:07:09 -07:00
self.dealer = draw_hand(self.np_random)
self.player = draw_hand(self.np_random)
Render API (#2671) * add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
2022-06-08 00:20:56 +02:00
_, dealer_card_value, _ = self._get_obs()
suits = ["C", "D", "H", "S"]
self.dealer_top_card_suit = self.np_random.choice(suits)
if dealer_card_value == 1:
self.dealer_top_card_value_str = "A"
elif dealer_card_value == 10:
self.dealer_top_card_value_str = self.np_random.choice(["J", "Q", "K"])
else:
self.dealer_top_card_value_str = str(dealer_card_value)
if self.render_mode == "human":
self.render()
return self._get_obs(), {}
def render(self):
try:
import pygame
except ImportError:
raise DependencyNotInstalled(
2022-09-08 10:10:07 +01:00
"pygame is not installed, run `pip install gymnasium[toy_text]`"
)
player_sum, dealer_card_value, usable_ace = self._get_obs()
screen_width, screen_height = 600, 500
card_img_height = screen_height // 3
card_img_width = int(card_img_height * 142 / 197)
spacing = screen_height // 20
bg_color = (7, 99, 36)
white = (255, 255, 255)
if not hasattr(self, "screen"):
pygame.init()
if self.render_mode == "human":
pygame.display.init()
self.screen = pygame.display.set_mode((screen_width, screen_height))
else:
pygame.font.init()
self.screen = pygame.Surface((screen_width, screen_height))
if not hasattr(self, "clock"):
self.clock = pygame.time.Clock()
self.screen.fill(bg_color)
def get_image(path):
cwd = os.path.dirname(__file__)
image = pygame.image.load(os.path.join(cwd, path))
return image
def get_font(path, size):
cwd = os.path.dirname(__file__)
font = pygame.font.Font(os.path.join(cwd, path), size)
return font
small_font = get_font(
os.path.join("font", "Minecraft.ttf"), screen_height // 15
)
dealer_text = small_font.render(
"Dealer: " + str(dealer_card_value), True, white
)
dealer_text_rect = self.screen.blit(dealer_text, (spacing, spacing))
def scale_card_img(card_img):
return pygame.transform.scale(card_img, (card_img_width, card_img_height))
dealer_card_img = scale_card_img(
get_image(
os.path.join(
"img",
f"{self.dealer_top_card_suit}{self.dealer_top_card_value_str}.png",
)
)
)
dealer_card_rect = self.screen.blit(
dealer_card_img,
(
screen_width // 2 - card_img_width - spacing // 2,
dealer_text_rect.bottom + spacing,
),
)
hidden_card_img = scale_card_img(get_image(os.path.join("img", "Card.png")))
self.screen.blit(
hidden_card_img,
(
screen_width // 2 + spacing // 2,
dealer_text_rect.bottom + spacing,
),
)
player_text = small_font.render("Player", True, white)
player_text_rect = self.screen.blit(
player_text, (spacing, dealer_card_rect.bottom + 1.5 * spacing)
)
large_font = get_font(os.path.join("font", "Minecraft.ttf"), screen_height // 6)
player_sum_text = large_font.render(str(player_sum), True, white)
player_sum_text_rect = self.screen.blit(
player_sum_text,
(
screen_width // 2 - player_sum_text.get_width() // 2,
player_text_rect.bottom + spacing,
),
)
if usable_ace:
usable_ace_text = small_font.render("usable ace", True, white)
self.screen.blit(
usable_ace_text,
(
screen_width // 2 - usable_ace_text.get_width() // 2,
player_sum_text_rect.bottom + spacing // 2,
),
)
if self.render_mode == "human":
pygame.event.pump()
pygame.display.update()
self.clock.tick(self.metadata["render_fps"])
else:
return np.transpose(
np.array(pygame.surfarray.pixels3d(self.screen)), axes=(1, 0, 2)
)
2022-03-15 00:41:02 -04:00
def close(self):
2022-05-13 13:58:19 +01:00
if hasattr(self, "screen"):
import pygame
pygame.display.quit()
pygame.quit()
2022-03-15 00:41:02 -04:00
# Pixel art from Mariia Khmelnytska (https://www.123rf.com/photo_104453049_stock-vector-pixel-art-playing-cards-standart-deck-vector-set.html)