package fehu

You can search for identifiers within the package.

in-package search v0.2.0

Reinforcement learning for OCaml

Install

dune-project

Dependency

github.com Readme Changelog Edit opam file Versions (3)

Authors

Thibaut Mattio

Maintainers

Thibaut Mattio

Sources

raven-1.0.0.alpha3.tbz

sha256=96d35ce03dfbebd2313657273e24c2e2d20f9e6c7825b8518b69bd1d6ed5870f

sha512=90c5053731d4108f37c19430e45456063e872b04b8a1bbad064c356e1b18e69222de8bfcf4ec14757e71f18164ec6e4630ba770dbcb1291665de5418827d1465

doc/fehu.envs/Fehu_envs/Grid_world/index.html

Module `Fehu_envs.Grid_world`Source

5x5 grid navigation with obstacle.

The agent starts at (0, 0) and must reach the goal at (4, 4). An obstacle at (2, 2) blocks movement. Reward is +10.0 on reaching the goal, -1.0 otherwise. Truncates at 200 steps.

Observation: Fehu.Space.spec.Multi_discrete [5; 5] -- (row, col).

Actions: Fehu.Space.spec.Discrete 4 -- 0 = up, 1 = down, 2 = left, 3 = right.

Render modes: ansi, rgb_array.

Sourcetype obs = (int32, Nx.int32_elt) Nx.t

Sourcetype act = (int32, Nx.int32_elt) Nx.t

Sourcetype render =

| Text of string
| Image of Fehu.Render.image

Source

val make : 
  ?render_mode:Fehu.Env.render_mode ->
  unit ->
  (obs, act, render) Fehu.Env.t

make () is a grid world environment.