AI4Finance-Foundation/ElegantRL

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

4355 stars · 978 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

machine-learning reinforcement-learning gpu-computing reinforcement-learning machine-learning deep-learning fintech python cloud pytorch ppo sac td3 dqn ddpg a2c model-free-rl massively-parallel cloud-native podracer gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AI4Finance-Foundation/ElegantRL")