# andri27-ts/Reinforcement-Learning

Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning

Repository: https://github.com/andri27-ts/Reinforcement-Learning
Canonical: https://ross.abutalabs.com/products/andri27-ts-reinforcement-learning
Homepage: https://andri27-ts.github.io/Reinforcement-Learning/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: reinforcement-learning, machine-learning, artificial-intelligence, deep-reinforcement-learning, deep-learning, policy-gradients, evolution-strategies, a2c, deepmind, dqn, qlearning, ppo
Last push: 2020-06-30T11:38:42+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": 2927, "days_push": 2255, "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 4737, forks 669 (observed 2026-08-28T04:08:57.747937+00:00)

## What it is
A 60-day structured course for learning Deep Reinforcement Learning, combining curated lectures (mainly from DeepMind and Berkeley) with PyTorch implementations of core algorithms like DQN, A2C, and PPO. Code is tested on OpenAI Gym environments including Atari and RoboSchool.

## Use cases
- learn deep reinforcement learning from scratch
- find a structured RL study plan
- see PyTorch implementations of DQN and PPO
- understand actor-critic and policy gradient algorithms
- practice RL algorithms on OpenAI Gym environments
- follow a 60-day reinforcement learning challenge

## When to choose
- you want a guided, time-boxed curriculum for deep RL
- you prefer learning by reading lectures and reading clean PyTorch code
- you already know basic Python, PyTorch, and deep learning fundamentals

## When to avoid
- you need a production-ready RL library or framework
- you want actively maintained code with recent updates (last release 2020)
- you are a complete beginner without ML or deep learning background

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, deep-learning, machine-learning
- domain: reinforcement-learning, deep-learning, machine-learning, tutorials, artificial-intelligence
- platform: python, cross-platform
- tags: pytorch, openai-gym, dqn, ppo, a2c, q-learning, policy-gradients, 60-days-challenge, jupyter-notebooks, course

## Member repositories
- andri27-ts/Reinforcement-Learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.747937+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 2026-08-29T18:18:59.022507+00:00, confidence not recorded.
  - readme: https://github.com/andri27-ts/Reinforcement-Learning (fetched 2026-08-28T04:08:57.747937+00:00, sha cc04a7c262f3)
  - homepage: https://andri27-ts.github.io/Reinforcement-Learning/ (fetched 2026-08-29T09:02:31.546673+00:00, sha e0592b56f611)
- Data as of 2026-08-30T08:39:29.467469+00:00.