Skip to main content

Gym Tool Use

gym tool use environments.


$ pip install gym-tool-use

Usage

import gym_tool_use  # import to register gym envs
env = gym.make("TrapTube-v0")
observation = env.reset()
action = env.action_space.sample()
observation_next, reward, done, info = env.step(action)
image = env.render(mode="rgb_array")  # also supports mode="human"

Environments

The following environments are registered:

  • "TrapTube-v0" (base task)
  • "PerceptualTrapTube-v0"
  • "StructuralTrapTube-v0"
  • "SymbolicTrapTube-v0"
  • "PerceptualSymbolicTrapTube-v0"
  • "StructuralSymbolicTrapTube-v0"
  • "PerceptualStructuralTrapTube-v0"
  • "PerceptualStructuralSymbolicTrapTube-v0"

Baselines

Baseline implementations here: https://github.com/fomorians/tool-use

Development

Development is started with pipenv.

$ pipenv install
$ pipenv shell

Metadata

Release files for gym-tool-use 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gym-tool-use 1.0.0
File Size Uploaded Provenance Actions
gym-tool-use-1.0.0.tar.gz 12.9 kB Without provenance Details for gym-tool-use-1.0.0.tar.gz

Release files / gym-tool-use-1.0.0.tar.gz

Download URL gym-tool-use-1.0.0.tar.gz
Size 12.9 kB
Tags Source
SHA-256 checksum
How to use checksums
fbb5f35c870c5b87901cd4e3b81cc7ef26c4a8d5123a503fb95374a10a06fc56
BLAKE2b-256 checksum
How to use checksums
b35416be6f7a6ffb5656af19f479c7d668e0db6850bfec17a42ba5777a359865
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.6.5

Security for gym-tool-use 1.0.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.0 This release

1 release file No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page