# rll/rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

Repository: https://github.com/rll/rllab
Canonical: https://ross.abutalabs.com/products/rllab
Language: Python
License: NOASSERTION
License Family: other
Last push: 2023-06-10T20:57:52+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3786, "days_push": 1180, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3078, forks 800 (observed 2026-08-28T04:07:41.842142+00:00)

## What it is
rllab is a Python framework for developing and evaluating reinforcement learning algorithms, with implementations of algorithms like TRPO, DDPG, and REINFORCE, plus continuous control tasks and OpenAI Gym compatibility. It is no longer under active development and has been succeeded by the actively maintained garage codebase from the rlworkgroup alliance.

## Use cases
- implement and evaluate reinforcement learning algorithms
- run policy gradient experiments like TRPO on continuous control tasks
- benchmark RL algorithms against OpenAI Gym environments
- run RL experiments at scale on an EC2 cluster
- reproduce classic RL research baselines from older papers

## When to choose
- you need to reproduce or extend legacy rllab-based research code
- you are studying the original implementations of TRPO, DDPG, or REPS
- you are working with an old project already built on rllab and cannot migrate

## When to avoid
- you are starting a new reinforcement learning project - use garage instead
- you need actively maintained code, updated dependencies, or modern TensorFlow/PyTorch support
- you need Python versions newer than 3.5 or current GPU tooling

## Facets
- artifact type: framework
- maturity: abandoned
- function: machine-learning, reinforcement-learning, benchmarking
- domain: reinforcement-learning, machine-learning
- platform: python
- tags: reinforcement-learning, openai-gym, policy-gradient, robotics, deprecated, superseded-by-garage, research, linux, macos

## Member repositories
- rll/rllab (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.842142+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 2026-08-30T07:27:52.868287+00:00, confidence not recorded.
  - readme: https://github.com/rll/rllab (fetched 2026-08-28T04:07:41.842142+00:00, sha fd529d69d91f)
- Data as of 2026-08-30T08:39:29.467469+00:00.