# TJU-DRL-LAB/AI-Optimizer

The next generation deep reinforcement learning tookit

Repository: https://github.com/TJU-DRL-LAB/AI-Optimizer
Canonical: https://ross.abutalabs.com/products/ai-optimizer
Language: Python
License Family: other
Topics: reinforcement-learning, transfer-learning, deep-learning
Last push: 2023-06-16T08:50:58+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1636, "days_push": 1174, "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 3465, forks 597 (observed 2026-08-28T04:08:05.756284+00:00)

## What it is
AI-Optimizer is a deep reinforcement learning toolkit from TJU's DRL lab offering algorithm libraries spanning model-free, model-based, offline, transfer, and multi-agent RL, plus a distributed training framework. It is primarily a research-oriented suite of reference implementations.

## Use cases
- train multi-agent reinforcement learning policies
- run model-based RL experiments
- train offline RL agents from datasets
- apply transfer learning to RL tasks
- learn self-supervised representation learning for RL
- distribute RL training across machines

## When to choose
- you need reference implementations of MARL, offline, or model-based RL algorithms for research
- you want a distributed RL training framework
- you are reproducing TJU-DRL-LAB research papers

## When to avoid
- you need a production-ready RL library with long-term support
- you require a permissive license - the repo has no license, so reuse is legally restricted
- you want a beginner-friendly, well-documented RL framework

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, reinforcement-learning, agent-framework
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: deep-reinforcement-learning, multi-agent-rl, model-based-rl, offline-rl, transfer-learning, distributed-training, research-toolkit, research, linux, gpu

## Member repositories
- TJU-DRL-LAB/AI-Optimizer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.756284+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 2026-08-29T18:36:52.379157+00:00, confidence not recorded.
  - readme: https://github.com/TJU-DRL-LAB/AI-Optimizer (fetched 2026-08-28T04:08:05.756284+00:00, sha 98de95a1c10f)
- Data as of 2026-08-30T08:39:29.467469+00:00.