CowHerd

CowHerd is a partially-observed reinforcement learning environment, where the player walks around an area and is rewarded for milking cows. The cows try to escape and the player can place fences to help capture them. The implementation of CowHerd is based on the Crafter environment.

Play Yourself

You can play the game yourself with an interactive window and keyboard input. The mapping from keys to actions, health level, and inventory state are printed to the terminal.

# Install with GUI
pip3 install 'cowherd[gui]'

# Start the game
cowherd

# Alternative way to start the game
python3 -m cowherd.run_gui

The following optional command line flags are available:

Training Agents

Installation: pip3 install -U cowherd

The environment follows the OpenAI Gym interface:

import cowherd

env = cowherd.Env(seed=0)
obs = env.reset()
assert obs.shape == (64, 64, 3)

done = False
while not done:
  action = env.action_space.sample()
  obs, reward, done, info = env.step(action)

Environment Details

Reward

A reward of +1 is given every time the player milks one of the cows.

Termination

Episodes terminate after 1000 steps.

Observation Space

Each observation is an RGB image that shows a local view of the world around the player, as well as the inventory state of the agent.

Action Space

The action space is categorical. Each action is an integer index representing one of the possible actions:

Questions

Please open an issue on Github.