Coach

Coach is a Python reinforcement learning (RL) research framework that bundles implementations of many state-of-the-art algorithms behind a set of simple,…

  • Monitoring & Logging
  • Productivity
  • Tools & Utilities
Coach is a Python reinforcement learning (RL) research framework that bundles implementations of many state-of-the-art algorithms behind a set of simple, decoupled APIs. It exposes easy-to-use interfaces for experimenting with new algorithms and integrating new environments on top of OpenAI Gym, which makes it a practical building block for anyone developing or studying RL agents.

Platform availability

Available on 0 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

6/100 Low

Maintained
0last commit 3319 days ago
Popular
00 GitHub stars
Easy to install
250 install platforms, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

GitHub stars
0
Open issues
0
Last commit
2017-10-20
License
Apache-2.0
Activity
stale

Checked 18 days ago - source: GitHub (tony8/coach)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install in a Python virtual environment Create and activate a virtual environment (a sandboxed area for one project's Python packages), then install Coach inside it with `pip install rl_coach`. This keeps Coach's dependencies from clashing with other Python tools and helps prevent failures that happen when package versions conflict. source
  • Installation Coach is tested on Ubuntu 16.04 LTS only. Its bundled installer sets up the required dependencies and it runs on top of OpenAI Gym environments; for example, train an agent with 'python coach.py -p CartPole_DQN -r'. source

Fetched 2 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How should I install Coach to avoid Python dependency conflicts?

Create and activate a Python virtual environment, then install Coach inside it with pip install rl_coach. This keeps Coach's dependencies from clashing with other Python tools and helps prevent package version conflicts.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads