# XinJingHao/DRL-Pytorch

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

Repository: https://github.com/XinJingHao/DRL-Pytorch
Canonical: https://ross.abutalabs.com/products/drl-pytorch
Language: Python
License Family: other
Topics: deep-reinforcement-learning, pytorch, reinforcement-learning, machine-learning, asl, c51, categorical-dqn, ddpg, double-dqn, dueling-dqn, noisynet-dqn, ppo, prioritized-experience-replay, q-learning, sac, td3
Last push: 2025-06-11T04:40:44+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 26, release rhythm 35, longevity 100
- inputs: {"age_days": 1753, "days_push": 448, "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 3436, forks 389 (observed 2026-08-28T04:08:04.915644+00:00)

## What it is
A unified PyTorch implementation collection of popular deep reinforcement learning algorithms including DQN variants, PPO, DDPG, TD3, SAC, and ASL. Each algorithm lives in its own folder with a main.py training script built on Gymnasium environments.

## Use cases
- implement deep reinforcement learning algorithms in pytorch
- learn how PPO works with clean code
- train a DQN agent on gymnasium environments
- compare SAC TD3 and DDPG implementations
- reference implementation for continuous control RL
- study reinforcement learning algorithms from scratch

## When to choose
- You want clean, readable reference implementations of classic DRL algorithms
- You are learning or teaching reinforcement learning with PyTorch
- You need a starting codebase to modify for your own RL experiments

## When to avoid
- You need a production RL training framework with distributed scaling
- You require a maintained, licensed library with API guarantees
- You want a high-level RL library like Stable-Baselines3 with unified APIs

## Facets
- artifact type: library
- maturity: active
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python, cross-platform
- tags: pytorch, dqn, ppo, sac, td3, ddpg, q-learning, gymnasium, education, gpu

## Member repositories
- XinJingHao/DRL-Pytorch (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.915644+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 2026-08-29T18:37:41.712049+00:00, confidence not recorded.
  - readme: https://github.com/XinJingHao/DRL-Pytorch (fetched 2026-08-28T04:08:04.915644+00:00, sha 1fb7d85f75e8)
- Data as of 2026-08-30T08:39:29.467469+00:00.