Skip to main content

Package to handle Reinforcement Learning functions. This package is nowhere near complete.

Project description

UmbrellaRL

This package is nowhere near complete.

Structure

  • Agent

The Agent represents the logic for reinforcement learning. It contains functions for policy evaluation & calculating a State's value.

  • Policy

The Policy object determines the actions taken by the agent. The Policy object must inherit from the Base Policy class.

  • Environment

The Environment represents the State that the Agent is in. It describes which states are accessible following actions & what their probabilities are.

The Environment depends on the State Space.

  • State Space

The State Space describes the states that the agent can be in. Each State is of type State.

The State Space depends on the State.

  • State

The State represents a singular State that the agent can be in. The State contains the information that describes each State.

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

umbrellarl-0.0.0.tar.gz (9.3 kB view details)

Uploaded Source

Built Distribution

umbrellarl-0.0.0-py3-none-any.whl (15.2 kB view details)

Uploaded Python 3

File details

Details for the file umbrellarl-0.0.0.tar.gz.

File metadata

  • Download URL: umbrellarl-0.0.0.tar.gz
  • Upload date:
  • Size: 9.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.12.0

File hashes

Hashes for umbrellarl-0.0.0.tar.gz
Algorithm Hash digest
SHA256 4a75d22fedcef9750a1896d16a4ede5e0a771172873ecf1e30266a66b20e2449
MD5 7abe10f80dec7892fcf2c04c922a480e
BLAKE2b-256 79f14f78a4675ac3621315070c6f8ca5b1ed23456a8d3fe35a59a706b92a5c46

See more details on using hashes here.

File details

Details for the file umbrellarl-0.0.0-py3-none-any.whl.

File metadata

  • Download URL: umbrellarl-0.0.0-py3-none-any.whl
  • Upload date:
  • Size: 15.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.12.0

File hashes

Hashes for umbrellarl-0.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c1b73c826bdbd7aef724bf15b2ada6bc88c4adb63dcab42fdff7996922a42c29
MD5 cd29e371a03c50e4bfe1a70cca105837
BLAKE2b-256 420f7da3bcabbc8c1f25dd40dfa2fb64b91631d4b30c0fa89f690ac0a2b0b643

See more details on using hashes here.

Supported by

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