Port details on branch 2022Q2 |
- py-gym OpenAI toolkit for developing and comparing your reinforcement learning agents
- 0.26.2_1 math =0 0.26.2_1Version of this port present on the latest quarterly branch.
- Maintainer: sunpoet@FreeBSD.org
- Port Added: 2019-06-21 23:09:29
- Last Update: 2023-06-27 19:34:34
- Commit Hash: 3d9a815
- Also Listed In: python
- License: MIT
- WWW:
- https://www.gymlibrary.dev/
- https://github.com/openai/gym
- Description:
- OpenAI Gym is a toolkit for developing and comparing reinforcement learning
algorithms. This is the gym open-source library, which gives you access to a
standardized set of environments.
gym makes no assumptions about the structure of your agent, and is compatible
with any numerical computation library, such as TensorFlow or Theano. You can
use it from Python code, and soon from other languages.
There are two basic concepts in reinforcement learning: the environment (namely,
the outside world) and the agent (namely, the algorithm you are writing). The
agent sends actions to the environment, and the environment replies with
observations and rewards (that is, a score).
The core gym interface is Env, which is the unified environment interface. There
is no interface for agents; that part is left to you. The following are the Env
methods you should know:
- reset(self): Reset the environment's state. Returns observation.
- step(self, action): Step the environment by one timestep. Returns observation,
reward, done, info.
- render(self, mode='human'): Render one frame of the environment. The default
mode will do something human friendly, such as pop up a window.
- ¦ ¦ ¦ ¦
- Manual pages:
- FreshPorts has no man page information for this port.
- pkg-plist: as obtained via:
make generate-plist - There is no configure plist information for this port.
- Dependency lines:
-
- ${PYTHON_PKGNAMEPREFIX}gym>0:math/py-gym@${PY_FLAVOR}
- To install the port:
- cd /usr/ports/math/py-gym/ && make install clean
- To add the package, run one of these commands:
- pkg install math/py-gym
- pkg install py39-gym
NOTE: If this package has multiple flavors (see below), then use one of them instead of the name specified above. NOTE: This is a Python port. Instead of py39-gym listed in the above command, you can pick from the names under the Packages section.- PKGNAME: py39-gym
- Package flavors (<flavor>: <package>)
- distinfo:
- TIMESTAMP = 1665073148
SHA256 (gym-0.26.2.tar.gz) = e0d882f4b54f0c65f203104c24ab8a38b039f1289986803c7d02cdbe214fbcc4
SIZE (gym-0.26.2.tar.gz) = 721689
Packages (timestamps in pop-ups are UTC):
- Dependencies
- NOTE: FreshPorts displays only information on required and default dependencies. Optional dependencies are not covered.
- Build dependencies:
-
- py39-setuptools>=63.1.0 : devel/py-setuptools@py39
- python3.9 : lang/python39
- Test dependencies:
-
- py39-pytest>=0 : devel/py-pytest@py39
- python3.9 : lang/python39
- Runtime dependencies:
-
- py39-cloudpickle>=1.2.0 : devel/py-cloudpickle@py39
- py39-gym-notices>=0.0.4 : math/py-gym-notices@py39
- py39-numpy>=1.18.0,1 : math/py-numpy@py39
- py39-setuptools>=63.1.0 : devel/py-setuptools@py39
- python3.9 : lang/python39
- py39-importlib-metadata>=4.8.0 : devel/py-importlib-metadata@py39
- This port is required by:
- for Run
-
- devel/py-bullet3
Configuration Options:
- No options to configure
- Options name:
- math_py-gym
- USES:
- python
- FreshPorts was unable to extract/find any pkg message
- Master Sites:
|