# tensorforce/tensorforce

Tensorforce: a TensorFlow library for applied reinforcement learning

Repository: https://github.com/tensorforce/tensorforce
Canonical: https://ross.abutalabs.com/products/tensorforce
Language: Python
License: Apache-2.0
License Family: permissive
Topics: reinforcement-learning, tensorflow, deep-reinforcement-learning, tensorflow-library, tensorforce, control, system-control
Last push: 2026-07-14T05:34:38+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 8, longevity 100
- inputs: {"age_days": 3454, "days_push": 50, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3305, forks 523 (observed 2026-08-28T04:07:55.832815+00:00)

## What it is
Tensorforce is an open-source deep reinforcement learning framework built on TensorFlow, emphasizing modular, configurable library design for research and applied RL. It separates RL algorithms from application environments and implements full models in TensorFlow computation graphs.

## Use cases
- train deep reinforcement learning agents in python
- apply RL to control and decision-making problems
- build modular configurable RL algorithms on tensorflow
- deploy trained RL policies as portable tensorflow graphs
- experiment with policy gradient and q-learning algorithms

## When to choose
- you need a flexible, modular RL library on TensorFlow
- you want algorithm-agnostic interfaces for custom environments
- you need portable TensorFlow-based RL models for deployment

## When to avoid
- you need an actively maintained library - the project is no longer maintained
- you prefer PyTorch-based RL frameworks
- you need the latest RL research algorithms

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, reinforcement-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: tensorflow, deep-reinforcement-learning, rl-library, control, unmaintained

## Member repositories
- tensorforce/tensorforce (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:55.832815+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:42:39.574619+00:00, confidence not recorded.
  - readme: https://github.com/tensorforce/tensorforce (fetched 2026-08-28T04:07:55.832815+00:00, sha 12cdccb6f3bb)
  - registry_pypi: https://pypi.org/pypi/tensorforce/json (fetched 2026-08-29T09:35:22.625534+00:00, sha 8330628c9c18)
- Data as of 2026-08-30T08:39:29.467469+00:00.