# AI4Finance-Foundation/ElegantRL

Massively Parallel Deep Reinforcement Learning. 🔥

Repository: https://github.com/AI4Finance-Foundation/ElegantRL
Canonical: https://ross.abutalabs.com/products/elegantrl
Homepage: https://ai4finance.org
Language: Python
License: NOASSERTION
License Family: other
Topics: pytorch, reinforcement-learning, ppo, sac, td3, dqn, ddpg, stable, lightweight, efficient, model-free-rl, drl-pytorch, gae, bipedalwalkerhardcore, per, multiple-gpu, a2c
Last push: 2026-02-20T04:33:56+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 68, release rhythm 8, longevity 100
- inputs: {"age_days": 2609, "days_push": 194, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4355, forks 978 (observed 2026-08-28T04:08:46.423565+00:00)

## What it is
ElegantRL is a lightweight, modular deep reinforcement learning library built on PyTorch that implements core model-free RL algorithms (PPO, SAC, TD3, DQN, DDPG, A2C) with minimal dependencies. It exploits massive parallelism to scale training elastically across hundreds or thousands of GPU nodes in cloud environments.

## Use cases
- train deep reinforcement learning agents in pytorch
- run massively parallel RL experiments on multiple GPUs
- implement PPO SAC TD3 DQN algorithms from scratch
- scale reinforcement learning training across cloud GPU clusters
- learn RL algorithms through clean readable code
- train trading agents with reinforcement learning

## When to choose
- you want a lightweight, dependency-minimal RL library with transparent algorithm implementations
- you need to scale DRL training across many GPUs or cloud nodes
- you want to experiment with or extend model-free RL algorithms in PyTorch

## When to avoid
- you need a mature ecosystem with many prebuilt environments and wrappers like Stable-Baselines3 or RLlib
- you need offline RL, model-based RL, or multi-agent RL out of the box
- you require a permissive, well-defined license for commercial use

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, reinforcement-learning, gpu-computing
- domain: reinforcement-learning, machine-learning, deep-learning, fintech
- platform: python, cloud
- tags: pytorch, ppo, sac, td3, dqn, ddpg, a2c, model-free-rl, massively-parallel, cloud-native, podracer, gpu, docker

## Member repositories
- AI4Finance-Foundation/ElegantRL (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.423565+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 2026-08-29T18:21:29.972276+00:00, confidence not recorded.
  - readme: https://github.com/AI4Finance-Foundation/ElegantRL (fetched 2026-08-28T04:08:46.423565+00:00, sha 64e4aad84fc7)
  - homepage: https://ai4finance.org (fetched 2026-08-29T09:10:19.742047+00:00, sha d3d3e0581dfb)
  - site_page: https://ai4finance.org/about (fetched 2026-08-29T09:10:19.751126+00:00, sha 38823c8faa4a)
- Data as of 2026-08-30T08:39:29.467469+00:00.