Skip to main content

Gridworlds environments for OpenAI gym.

Project description

Implementation of three gridworlds environments from book Reinforcement Learning: An Introduction compatible with OpenAI gym.

Usage

$ import gym
$ import gym_gridworlds
$ env = gym.make('Gridworld-v0')  # substitute environment's name

Gridworld-v0

Gridworld is simple 4 times 4 gridworld from example 4.1 in the [book]. There are fout action in each state (up, down, right, left) which deterministically cause the corresponding state transitions but actions that would take an agent of the grid leave a state unchanged. The reward is -1 for all tranistion until the terminal state is reached. The terminal state is in top left and bottom right coners.

WindyGridworld-v0

Windy gridworld is from example 6.5 in the book. Windy gridworld is a standard gridworld as described above but there is a crosswind upward through the middle of the grid. Action are standard but in the middle region the resultant states are shifted upward by a wind which strength varies between columns.

Cliff-v0

Cliff walking is a gridworld example 6.6 from the book. Again reward is -1 on all transition except those into region that is cliff. Stepping into this region incurs a reward of -100 and sends the agent instantly back to the start.

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

gym_gridworlds-0.0.2.tar.gz (3.7 kB view hashes)

Uploaded source

Built Distribution

gym_gridworlds-0.0.2-py3-none-any.whl (5.9 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page