hcraft 1.2.3

Lightweight environments to study hierarchical reasoning

HierarchyCraft - Environements builder for hierarchical ML research

HierarchyCraft

HierarchyCraft (hcraft for short) is a Python library designed to create arbitrary hierarchical environments that are compatible with both the OpenAI Gym Reinforcement Learning Framework and AIPlan4EU Unified Planning Framework. This library enables users to easily create complex hierarchical structures that can be used to test and develop various reinforcement learning or planning algorithms.

In environments built with HierarchyCraft the agent (player) has an inventory and can navigate into abstract zones that themselves have inventories.

Available actions of the agent are defined by transformations. Transformations are the core element of every HierarchyCraft environment, they define the actions that an agent can perform in the environment. At their core, transformations are simply changes to the state of the environment that can be triggered by the agent if the transformation is allowed in the current state.

No feature extraction for fast research even with low compute

HierarchyCraft returns vectorized state information, which plainly and directly describes the player's inventory, current positions, and the inventory of the current zone. Compared to benchmarks that return grids, pixel arrays, text or sound, we directly return a low-dimensional latent representation that doesn't need to be learned. Therefore saving compute time and allowing researchers to focus only the the hierarchical reasoning part.

See hcraft.state for more details.

Create your own tailored HierarchyCraft environments

You can use HierarchyCraft to create various custom hierarchical environments. As a showcase of the complexe possibilities, here is a replica of the underlying hierarchy of the popular game Minecraft, without the computationaly intensive 3D and without being a 2D grid version either.

See hcraft.env for a complete tutorial on creating custom environments.

Installation

Using pip

Without optional dependencies:

pip install hcraft

With all optional dependencies:

pip install hcraft[all]

All hcraft environments can use a common graphical user interface. With gui requirements:

pip install hcraft[gui]

Gym environment can be obtained throught the with gym requirements:

pip install hcraft[gym]

Planning problems can be obtained throught the upf interface:

pip install hcraft[planning]

Quickstart

Play yourself!

Don't forget to install the GUI:

pip install hcraft[gui]

Using the command line interface

You can directly try to play yourself with the GUI available for any HierarchyCraft environments, for example:

hcraft minecraft

For more examples:

hcraft --help

Using the programmatic interface:

from hcraft import MineHcraftEnv, get_human_action

env = MineHcraftEnv()
# or env: MineHcraftEnv = gym.make("MineHcraft-NoReward-v1")
n_episodes = 2
for _ in range(n_episodes):
    env.reset()
    done = False
    total_reward = 0
    while not done:
        env.render()
        action = get_human_action(env)
        print(f"Human pressed: {env.world.transformations[action]}")

        _observation, reward, done, _info = env.step(action)
        total_reward += reward

    print(f"SCORE: {total_reward}")

As a Gym RL environment

Using the programmatic interface, any HierarchyCraft environment can easily be interfaced with classic reinforcement learning agents.

import numpy as np
from hcraft import MineHcraftEnv

def random_legal_agent(observation, action_is_legal):
    action = np.random.choice(np.nonzero(action_is_legal)[0])
    return int(action)

env = MineHcraftEnv(max_step=10)
done = False
observation = env.reset()
while not done:
    action_is_legal = env.action_masks()
    action = random_legal_agent(observation, action_is_legal)
    _observation, _reward, done, _info = env.step(action)

# Other HierarchyCraft environments
from hcraft import TowerHcraft, RecursiveHcraft, RandomHcraft

tower_env = TowerHcraft(height=3, width=2)
# or tower_env = gym.make("TowerHcraft-v1", height=3, width=2)
recursive_env = RecursiveHcraft(n_items=6)
# or recursive_env = gym.make("RecursiveHcraft-v1", n_items=6)
random_env = RandomHcraft(n_items_per_n_inputs={0:2, 1:5, 2:10}, seed=42)
# or random_env = gym.make("RandomHcraft-v1", n_items_per_n_inputs={0:2, 1:5, 2:10}, seed=42)

See hcraft.env for a more complete description.

As a UPF problem for planning

HierarchyCraft environments can be converted to planning problem in one line thanks to the Unified Planning Framework (UPF):

problem = env.planning_problem()
print(problem.upf_problem)

Then they can be solved with any compatible planner (default is enhsp):

problem.solve()
print(problem.plan)

See hcraft.planning for a more complete description.

More about HierarchyCraft

Online documentation

Learn more in the DOCUMENTATION