reinforce: Reinforcement learning in Haskell

This is a package candidate release! Here you can preview how this package release will appear once published to the main package index (which can be accomplished via the 'maintain' link below). Please note that once a package has been published to the main package index it cannot be undone! Please consult the package uploading documentation for more information.

[maintain] [Publish]

Warnings:

Exposed modules use unallocated top-level names: Environments Reinforce

See README.md. reinforce is a library which exports an OpenAI-gym-like typeclass, MonadEnv, with both an interface to the gym-http-api, as well as haskell-native environments which provide a substantial speed-up to the http-server interface. This is an environment-first library, with basic reinforcment learning algorithms being developed on branches in subpackages (see Development and Milestones). reinforce is currently an "alpha" release since it still needs some work defining some formal structures around what state-spaces and action-spaces should look like, however haskell's typesystem is expressive enough that this seems to be more of a "nice-to-have." It's in active development and has some beginner-friendly contributions - from porting new gym environments to implementing new algorithms.

Properties

Versions	0.0.0.1
Change log	None available
Dependencies	aeson (==1.0.2.1), base (>=4.9 && <=4.10), dlist (==0.8.0.2), gym-http-api, hashable (==1.2.5.0), hmatrix (==0.18.0.0), http-client (==0.5.6.1), mtl (==2.2.1), mwc-random (==0.13.5.0), primitive (==0.6.1.0), reinforce, safe-exceptions (==0.1.5.0), servant-client (==0.9.1.1), statistics (==0.13.3.0), text (==1.2.2.1), vector (==0.11.0.0) [details]
License	BSD-3-Clause
Copyright	2017 Sentenai, Inc.
Author	Sam Stites, Sentenai Inc.
Maintainer	sam@sentenai.com
Category	Reinforcement learning, machine learning, artificial intelligence
Home page	https://github.com/Sentenai/reinforce#readme
Bug tracker	https://github.com/Sentenai/reinforce/issues
Source repo	head: git clone https://github.com/Sentenai/reinforce
Uploaded	by stites at 2017-07-31T22:21:46Z

Modules

Control
- Control.MonadEnv
- Control.MonadMWCRandom
Data
- Data.CartPole
- Data.Logger
Environments
- Environments.Bandits
- Environments.CartPole
- Gym
  - ClassicControl
    - Environments.Gym.ClassicControl.AcrobotV1
    - Environments.Gym.ClassicControl.CartPoleV0
    - Environments.Gym.ClassicControl.CartPoleV1
    - Environments.Gym.ClassicControl.MountainCarContinuousV0
    - Environments.Gym.ClassicControl.MountainCarV0
    - Environments.Gym.ClassicControl.PendulumV0
  - Environments.Gym.Internal
  - ToyText
    - Environments.Gym.ToyText.FrozenLakeV0
Reinforce
- Reinforce.Prelude
- Reinforce.Spaces
  - Reinforce.Spaces.Action
  - Reinforce.Spaces.State

Downloads

reinforce-0.0.0.1.tar.gz [browse] (Cabal source package)
Package description (as included in the package)

Maintainer's Corner

Package maintainers

stites

For package maintainers and hackage trustees

edit package information