Skip to main content

Visual reinforcement learning benchmark for controllability.

Project description

BridgeWalk

PyPI

BridgeWalk is a partially-observed reinforcement learning environment with dynamics of varying stochasticity. The player needs to walk along a bridge to reach a goal location. When the player walks off the bridge into the water, the current will move it randomly until it gets washed back on the shore. A good agent in this environment avoids this stochastic trap. The implementation of BridgeWalk is based on the Crafter environment.

Bridge Walk Video

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 'bridgewalk[gui]'

# Start the game
bridgewalk

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

The following optional command line flags are available:

Flag Default Description
--window <width> <height> 800 800 Window size in pixels, used as width and height.
--fps <integer> 5 How many times to update the environment per second.
--record <filename>.mp4 None Record a video of the trajectory.
--view <width> <height> 7 7 The layout size in cells; determines view distance.
--length <integer> None Time limit for the episode.
--seed <integer> None Determines world generation and creatures.

Training Agents

Installation: pip3 install -U bridgewalk

The environment follows the OpenAI Gym interface:

import bridgewalk

env = bridgewalk.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 the first time in each episode when the agent reaches the island at the end of the bridge.

Termination

Episodes terminate after 250 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:

Integer Name Description
0 noop Do nothing.
1 move_left Walk left.
2 move_right Walk right.
3 move_up Walk up.
4 move_down Walk down.

Questions

Please open an issue on Github.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bridgewalk-0.1.0.tar.gz (30.0 kB view details)

Uploaded Source

File details

Details for the file bridgewalk-0.1.0.tar.gz.

File metadata

  • Download URL: bridgewalk-0.1.0.tar.gz
  • Upload date:
  • Size: 30.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.2

File hashes

Hashes for bridgewalk-0.1.0.tar.gz
Algorithm Hash digest
SHA256 57ca59c82d597753f9ff58075f25d423481bb3fe539893ed2560394aaf1ba048
MD5 4aebfc2d2f0afbc5f909b909ea57fda6
BLAKE2b-256 7ba9b383fca4f4ea03bbae835020f68c44081e6a2724437015cd58cebb1a1075

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page