# udacity/deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program

Repository: https://github.com/udacity/deep-reinforcement-learning
Canonical: https://ross.abutalabs.com/products/deep-reinforcement-learning
Homepage: https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-reinforcement-learning, reinforcement-learning, reinforcement-learning-algorithms, neural-networks, pytorch, pytorch-rl, ddpg, dqn, ppo, dynamic-programming, cross-entropy, hill-climbing, ml-agents, openai-gym-solutions, openai-gym, rl-algorithms
Last push: 2026-07-08T18:11:48+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 35, longevity 100
- inputs: {"age_days": 2980, "days_push": 56, "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 5176, forks 2373 (observed 2026-08-28T04:09:11.745797+00:00)

## What it is
The official repository of Jupyter Notebook tutorials and exercises for Udacity's Deep Reinforcement Learning Nanodegree program. It provides PyTorch-based implementations of classic and deep RL algorithms such as dynamic programming, DQN, PPO, and DDPG, mostly using OpenAI Gym environments.

## Use cases
- learn reinforcement learning from scratch with hands-on notebooks
- implement DQN to solve an OpenAI Gym environment
- study policy gradient methods like REINFORCE and PPO
- understand temporal-difference learning such as Q-Learning and Sarsa
- practice discretizing continuous state spaces with tile coding
- find reference solutions for OpenAI Gym RL exercises

## When to choose
- you want structured, tutorial-style notebooks for learning deep RL
- you prefer PyTorch implementations of classic RL algorithms
- you are following or supplementing Udacity's Deep RL Nanodegree

## When to avoid
- you need a production-ready RL library or framework
- you want state-of-the-art algorithms beyond the course scope
- you need actively maintained code compatible with modern PyTorch versions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: pytorch, openai-gym, dqn, ppo, ddpg, nanodegree, jupyter-notebooks, udacity

## Member repositories
- udacity/deep-reinforcement-learning (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.745797+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 2026-08-29T18:01:49.878627+00:00, confidence not recorded.
  - readme: https://github.com/udacity/deep-reinforcement-learning (fetched 2026-08-28T04:09:11.745797+00:00, sha ab0d8093f29f)
  - homepage: https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893 (fetched 2026-08-29T08:55:44.539869+00:00, sha 3afe4b2c1afe)
- Data as of 2026-08-30T08:39:29.467469+00:00.