# Rafael1s/Deep-Reinforcement-Learning-Algorithms

32 projects in the framework of Deep Reinforcement Learning algorithms: Q-learning, DQN, PPO, DDPG, TD3, SAC, A2C and others. Each project is provided with a detailed training log.

Repository: https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms
Canonical: https://ross.abutalabs.com/products/deep-reinforcement-learning-algorithms
Language: Jupyter Notebook
License Family: other
Topics: deep-rl-algorithms, github-udacity, dqn-ppo-ddpg, dqn, td3, cartpole, bipedalwalker, deep-reinforcement-learning, sac, carracing, hopperbulletenv, lunarlander, ddpg, ppo, a2c, antbulletenv, soft-actor-critic, halfcheetahbulletenv, walker2dbulletenv
Last push: 2021-06-17T21:58:26+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2705, "days_push": 1903, "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 1031, forks 231 (observed 2026-08-28T04:03:17.875707+00:00)

## What it is
A collection of 32 Jupyter Notebook projects implementing deep reinforcement learning algorithms such as Q-learning, DQN, PPO, DDPG, TD3, SAC, and A2C across many environments like CartPole, LunarLander, and BipedalWalker. Each project includes a detailed training log, making it a reference and educational resource for studying RL methods.

## Use cases
- learn deep reinforcement learning algorithms with worked examples
- see training logs for DQN on CartPole or LunarLander
- compare PPO vs DDPG vs TD3 vs SAC implementations
- study policy-gradient and actor-critic methods in notebooks
- find reference implementations for Udacity DRL nanodegree projects
- understand how to solve continuous control environments like BipedalWalker

## When to choose
- you want readable notebook-style implementations of classic deep RL algorithms
- you are studying RL and want to see full training logs and results
- you need reference code for Udacity DRL nanodegree environments

## When to avoid
- you need a production-ready or maintained RL library with an API
- you want a single unified framework rather than 32 separate notebooks
- you need actively updated code or official license terms

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, data-science
- domain: reinforcement-learning, machine-learning, tutorials, education
- platform: python, jvm
- tags: deep-reinforcement-learning, jupyter-notebooks, dqn, ppo, ddpg, td3, sac, a2c, q-learning, udacity, training-logs, pybullet, cartpole, lunarlander

## Member repositories
- Rafael1s/Deep-Reinforcement-Learning-Algorithms (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.875707+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 2026-08-30T07:07:25.101281+00:00, confidence not recorded.
  - readme: https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms (fetched 2026-08-28T04:03:17.875707+00:00, sha e67187f91c75)
- Data as of 2026-08-30T08:39:29.467469+00:00.