diff --git a/docs/_static/screenshots/breakable-bottles.jpg b/docs/_static/screenshots/breakable-bottles.jpg
deleted file mode 100644
index 851fc8d0..00000000
Binary files a/docs/_static/screenshots/breakable-bottles.jpg and /dev/null differ
diff --git a/docs/_static/screenshots/breakable-bottles.png b/docs/_static/screenshots/breakable-bottles.png
new file mode 100644
index 00000000..b4fe5b3e
Binary files /dev/null and b/docs/_static/screenshots/breakable-bottles.png differ
diff --git a/docs/_static/videos/breakable-bottles.gif b/docs/_static/videos/breakable-bottles.gif
new file mode 100644
index 00000000..4f901d79
Binary files /dev/null and b/docs/_static/videos/breakable-bottles.gif differ
diff --git a/docs/environments/all-environments.md b/docs/environments/all-environments.md
index b39b3ee7..802b6cc2 100644
--- a/docs/environments/all-environments.md
+++ b/docs/environments/all-environments.md
@@ -13,7 +13,7 @@ MO-Gymnasium includes environments taken from the MORL literature, as well as mu
| [`deep-sea-treasure-concave-v0`](https://mo-gymnasium.farama.org/environments/deep-sea-treasure-concave/)
| Discrete / Discrete | `[treasure, time_penalty]` | Agent is a submarine that must collect a treasure while taking into account a time penalty. Treasures values taken from [Vamplew et al. 2010](https://link.springer.com/article/10.1007/s10994-010-5232-5). |
| [`resource-gathering-v0`](https://mo-gymnasium.farama.org/environments/resource-gathering/)
| Discrete / Discrete | `[enemy, gold, gem]` | Agent must collect gold or gem. Enemies have a 10% chance of killing the agent. From [Barret & Narayanan 2008](https://dl.acm.org/doi/10.1145/1390156.1390162). |
| [`fishwood-v0`](https://mo-gymnasium.farama.org/environments/fishwood/)
| Discrete / Discrete | `[fish_amount, wood_amount]` | ESR environment, the agent must collect fish and wood to light a fire and eat. From [Roijers et al. 2018](https://www.researchgate.net/publication/328718263_Multi-objective_Reinforcement_Learning_for_the_Expected_Utility_of_the_Return). |
-| [`breakable-bottles-v0`](https://mo-gymnasium.farama.org/environments/breakable-bottles/)
| Discrete (Dictionary) / Discrete | `[time_penalty, bottles_delivered, potential]` | Gridworld with 5 cells. The agents must collect bottles from the source location and deliver to the destination. From [Vamplew et al. 2021](https://www.sciencedirect.com/science/article/pii/S0952197621000336). |
+| [`breakable-bottles-v0`](https://mo-gymnasium.farama.org/environments/breakable-bottles/)
| Discrete (Dictionary) / Discrete | `[time_penalty, bottles_delivered, potential]` | Gridworld with 5 cells. The agents must collect bottles from the source location and deliver to the destination. From [Vamplew et al. 2021](https://www.sciencedirect.com/science/article/pii/S0952197621000336). |
| [`fruit-tree-v0`](https://mo-gymnasium.farama.org/environments/fruit-tree/)
| Discrete / Discrete | `[nutri1, ..., nutri6]` | Full binary tree of depth d=5,6 or 7. Every leaf contains a fruit with a value for the nutrients Protein, Carbs, Fats, Vitamins, Minerals and Water. From [Yang et al. 2019](https://arxiv.org/pdf/1908.08342.pdf). |
| [`water-reservoir-v0`](https://mo-gymnasium.farama.org/environments/water-reservoir/)
| Continuous / Continuous | `[cost_flooding, deficit_water]` | A Water reservoir environment. The agent executes a continuous action, corresponding to the amount of water released by the dam. From [Pianosi et al. 2013](https://iwaponline.com/jh/article/15/2/258/3425/Tree-based-fitted-Q-iteration-for-multi-objective). |
| [`four-room-v0`](https://mo-gymnasium.farama.org/environments/four-room/)
| Discrete / Discrete | `[item1, item2, item3]` | Agent must collect three different types of items in the map and reach the goal. From [Alegre et al. 2022](https://proceedings.mlr.press/v162/alegre22a.html). |
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/Minecraft.ttf b/mo_gymnasium/envs/breakable_bottles/assets/Minecraft.ttf
new file mode 100644
index 00000000..85c14725
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/Minecraft.ttf differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/bottle.png b/mo_gymnasium/envs/breakable_bottles/assets/bottle.png
new file mode 100644
index 00000000..b1ff5983
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/bottle.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/elf_left.png b/mo_gymnasium/envs/breakable_bottles/assets/elf_left.png
new file mode 100644
index 00000000..bc9e22ea
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/elf_left.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/elf_right.png b/mo_gymnasium/envs/breakable_bottles/assets/elf_right.png
new file mode 100644
index 00000000..83640315
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/elf_right.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/home.png b/mo_gymnasium/envs/breakable_bottles/assets/home.png
new file mode 100644
index 00000000..565d371b
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/home.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg1.png b/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg1.png
new file mode 100644
index 00000000..e5872ceb
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg1.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg2.png b/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg2.png
new file mode 100644
index 00000000..8cadf7df
Binary files /dev/null and b/mo_gymnasium/envs/breakable_bottles/assets/mountain_bg2.png differ
diff --git a/mo_gymnasium/envs/breakable_bottles/breakable_bottles.py b/mo_gymnasium/envs/breakable_bottles/breakable_bottles.py
index 8c8abcbd..0a6cbe72 100644
--- a/mo_gymnasium/envs/breakable_bottles/breakable_bottles.py
+++ b/mo_gymnasium/envs/breakable_bottles/breakable_bottles.py
@@ -1,6 +1,9 @@
+from os import path
from typing import Optional
+import gymnasium as gym
import numpy as np
+import pygame
from gymnasium import Env
from gymnasium.spaces import Box, Dict, Discrete, MultiBinary
from gymnasium.utils import EzPickle
@@ -47,9 +50,12 @@ class BreakableBottles(Env, EzPickle):
## Credits
This environment was originally a contribution of Robert Klassert
+ The home asset is from https://limezu.itch.io/serenevillagerevamped
+ The gold, enemy and gem assets are from https://ninjikin.itch.io/treasure
+ The bottles pixel art was created with the assistance of DALL·E 2.
"""
- metadata = {"render_modes": ["human"]}
+ metadata = {"render_modes": ["human", "rgb_array"], "render_fps": 4}
# actions
LEFT = 0
@@ -103,7 +109,25 @@ def __init__(
self.reward_space = Box(np.array([-np.inf, 0, -1]), np.array([0, self.bottle_reward * 2, 0]))
self.reward_dim = 3
+ # pygame
+ self.cell_size = (64, 64)
+ self.window_size = (
+ self.size * self.cell_size[1],
+ 1 * self.cell_size[0],
+ )
+ self.clock = None
+ self.elf_images = []
+ self.home_img = None
+ self.bottle_img = None
+ self.mountain_bg_img = []
+ self.window = None
+ self.last_action = None
+ self.direction = self.RIGHT
+
def step(self, action):
+ self.last_action = action
+ if self.last_action != self.PICKUP:
+ self.direction = self.last_action
observation_old = self._get_obs()
old_potential = self.potential(observation_old)
terminal = False
@@ -207,12 +231,80 @@ def _get_obs(self):
}
def render(self):
- if self.render_mode == "human":
- print("-----")
- print(
- f"Location: {self.location}\nCarrying {self.bottles_carrying} bottles.\nDelivered {self.bottles_delivered} so far.\nBottles have been dropped at tiles {'1' if self.bottles_dropped[0] > 0 else ''} {'2' if self.bottles_dropped[1] > 0 else ''} {'3' if self.bottles_dropped[2] > 0 else ''}"
+ if self.render_mode is None:
+ assert self.spec is not None
+ gym.logger.warn(
+ "You are calling render method without specifying any render mode. "
+ "You can specify the render_mode at initialization, "
+ f'e.g. mo_gym.make("{self.spec.id}", render_mode="rgb_array")'
)
- print("-----")
+ return
+
+ if self.window is None:
+ pygame.init()
+
+ if self.render_mode == "human":
+ pygame.display.init()
+ pygame.display.set_caption("Breakable Bottles")
+ self.window = pygame.display.set_mode(self.window_size)
+ else:
+ self.window = pygame.Surface(self.window_size)
+
+ if self.clock is None:
+ self.clock = pygame.time.Clock()
+
+ if not self.elf_images:
+ hikers = [
+ path.join(path.dirname(__file__), "assets/elf_left.png"),
+ path.join(path.dirname(__file__), "assets/elf_right.png"),
+ ]
+ self.elf_images = [pygame.transform.scale(pygame.image.load(f_name), self.cell_size) for f_name in hikers]
+ if not self.mountain_bg_img:
+ bg_imgs = [
+ path.join(path.dirname(__file__), "assets/mountain_bg1.png"),
+ path.join(path.dirname(__file__), "assets/mountain_bg2.png"),
+ ]
+ self.mountain_bg_img = [
+ pygame.transform.scale(pygame.image.load(f_name), self.cell_size) for f_name in bg_imgs
+ ]
+ if self.home_img is None:
+ self.home_img = pygame.transform.scale(
+ pygame.image.load(path.join(path.dirname(__file__), "assets/home.png")),
+ self.cell_size,
+ )
+ if self.bottle_img is None:
+ self.bottle_img = pygame.transform.scale(
+ pygame.image.load(path.join(path.dirname(__file__), "assets/bottle.png")),
+ (32, 32),
+ )
+ self.font = pygame.font.Font(path.join(path.dirname(__file__), "assets", "Minecraft.ttf"), 10)
+
+ for i in range(self.size):
+ self.window.blit(
+ self.mountain_bg_img[i % 2],
+ np.array([i, 0]) * self.cell_size[0],
+ )
+ if i == 0:
+ for k in range(4):
+ self.window.blit(self.bottle_img, np.array([i, 0]) * self.cell_size[0] + np.array([k * 10, 0]))
+ if i == self.size - 1:
+ self.window.blit(self.home_img, np.array([i, 0]) * self.cell_size[0])
+ if i == self.location:
+ self.window.blit(self.elf_images[self.direction], np.array([i, 0]) * self.cell_size[0])
+ if i in range(1, self.size - 1):
+ if self.bottles_dropped[i - 1] > 0:
+ self.window.blit(self.bottle_img, np.array([i, 0]) * self.cell_size[0])
+ img = self.font.render(f"Carrying: {self.bottles_carrying}", True, (0, 0, 0))
+ self.window.blit(img, np.array([self.location, 0]) * self.cell_size + np.array([5, 50]))
+ img = self.font.render(f"Delivered: {self.bottles_delivered}", True, (0, 0, 0))
+ self.window.blit(img, np.array([self.size - 1, 0]) * self.cell_size + np.array([4, 5]))
+
+ if self.render_mode == "human":
+ pygame.event.pump()
+ pygame.display.update()
+ self.clock.tick(self.metadata["render_fps"])
+ elif self.render_mode == "rgb_array": # rgb_array
+ return np.transpose(np.array(pygame.surfarray.pixels3d(self.window)), axes=(1, 0, 2))
def close(self):
pass
@@ -224,16 +316,13 @@ def potential(self, obs):
if __name__ == "__main__":
- from gymnasium.spaces.utils import flatdim
+ import mo_gymnasium as mo_gym
- env = BreakableBottles(size=5, prob_drop=0.1)
- assert flatdim(env.action_space) == 3
- assert flatdim(env.observation_space) == 13
+ env = mo_gym.make("breakable-bottles-v0", render_mode="human")
done = False
- obs = env.reset()
+ obs, info = env.reset()
while True:
- env.render()
- obs, r, done, info = env.step(env.action_space.sample())
- if done:
+ obs, r, terminated, truncated, info = env.step(env.action_space.sample())
+ if terminated or truncated:
break