# Lizhi-sjtu/DRL-code-pytorch

Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

Repository: https://github.com/Lizhi-sjtu/DRL-code-pytorch
Canonical: https://ross.abutalabs.com/products/drl-code-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: ddpg-pytorch, dqn-pytorch, ppo-pytorch, pytorch, rainbow-dqn, reinforcement-learning, sac-pytorch, td3-pytorch, ppo-gru, ppo-lstm
Last push: 2023-03-29T07:13:37+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": 1624, "days_push": 1253, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1486, forks 208 (observed 2026-08-28T04:04:51.921121+00:00)

## What it is
A collection of concise PyTorch implementations of deep reinforcement learning algorithms including REINFORCE, A2C, Rainbow DQN, PPO, DDPG, TD3, and SAC. It serves as a clean, readable reference for learning and studying DRL algorithm implementations.

## Use cases
- learn how PPO is implemented in pytorch
- study DQN and Rainbow DQN code
- reference implementation of SAC or TD3
- understand discrete vs continuous PPO
- example code for a reinforcement learning course
- compare DRL algorithm implementations side by side

## When to choose
- you want readable, minimal implementations of classic DRL algorithms to learn from
- you need a starting point to modify or experiment with RL algorithms in PyTorch
- you are teaching or studying reinforcement learning and want reference code

## When to avoid
- you need a production-grade, feature-complete RL training framework with parallel environments
- you need maintained, up-to-date code compatible with current PyTorch and Gym versions
- you need benchmarking infrastructure or hyperparameter tuning tooling

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, reinforcement-learning
- domain: reinforcement-learning, machine-learning, tutorials
- platform: python
- tags: pytorch, drl, ppo, dqn, sac, ddpg, td3, a2c, reinforce, educational

## Member repositories
- Lizhi-sjtu/DRL-code-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.921121+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 2026-08-30T04:33:50.057944+00:00, confidence not recorded.
  - readme: https://github.com/Lizhi-sjtu/DRL-code-pytorch (fetched 2026-08-28T04:04:51.921121+00:00, sha 0d39100d846e)
- Data as of 2026-08-30T08:39:29.467469+00:00.