reinforcejs

Source

• Source kind: github-repository
• URL: https://github.com/karpathy/reinforcejs
• Discovery source: https://github.com/karpathy/reinforcejs
• License: NOASSERTION
• Distribution policy: public-summary-local-archive-only
• Public mirror status: summary-only
• Content hash: 6bc7e18b4b0a378035212d3f1f8302d2f15f1a556c90228df263981a76211e21
• First seen: 2026-05-15
• Last changed: 2026-05-15

Classification

• Primary category: Research automation / agentic science
• Corpus source note: 2026-05-15-karpathy-public-corpus
• Project taxonomy: karpathy-project-taxonomy
• Idea map: karpathy-idea-map
• Topic hub: karpathy-public-work

Summary

REINFORCEjs REINFORCEjs is a Reinforcement Learning library that implements several common RL algorithms, all with web demos. In particular, the library currently includes: - Dynamic Programming methods - (Tabular) Temporal Difference Learning (SARSA/Q-Learning) - Deep Q-Learning for Q-Learning with function approximation with Neural Networks - Stochastic/Deterministic Policy Gradients and Actor Critic architectures for dealing with continuous action spaces. ( very alpha, likely buggy or at the very least finicky and inconsistent ) See the $1 for many more details, documentation and demos. Code Sketch The library…

What This Teaches

• How Karpathy frames autonomous research loops, experiment iteration, and AI-assisted discovery.
• Useful for designing agent workflows that improve through concrete experiments instead of one-off prompting.

Why It Matters

This is high-priority for Vipin because it informs agent workflows, paper digestion, wiki maintenance, and autonomous research loops.

Repository Snapshot

• Full name: karpathy/reinforcejs
• Default branch: master
• HEAD: 08d2030d13b6a64ee4dd4ed75d1cd273a46aa8de
• Stars at crawl: 1463
• Forks at crawl: 354
• File count: 43
• README path: README.md
• License path: “
• Created: 2015-04-19T02:35:59Z
• Updated: 2026-05-13T16:22:41Z
• Pushed: 2019-02-18T20:11:56Z

Top-Level Structure

• external: 26
• [root]: 8
• img: 6
• agentzoo: 2
• lib: 1

File Extension Profile

• .png: 18
• .js: 11
• .html: 5
• .css: 2
• .jpeg: 2
• .json: 2
• .ds_store: 1
• .md: 1
• .svg: 1

Tags / Release-Like Markers

• No git tags found in the shallow local clone.

Sample File Tree

• agentzoo/puckagent.json
• agentzoo/wateragent.json
• external/.DS_Store
• external/d3.min.js
• external/highlight.pack.js
• external/highlight_default.css
• external/images/ui-bg_diagonals-thick_18_b81900_40x40.png
• external/images/ui-bg_diagonals-thick_20_666666_40x40.png
• external/images/ui-bg_flat_10_000000_40x100.png
• external/images/ui-bg_glass_100_f6f6f6_1x400.png
• external/images/ui-bg_glass_100_fdf5ce_1x400.png
• external/images/ui-bg_glass_65_ffffff_1x400.png
• external/images/ui-bg_gloss-wave_35_f6a828_500x100.png
• external/images/ui-bg_highlight-soft_100_eeeeee_1x100.png
• external/images/ui-bg_highlight-soft_75_ffe45c_1x100.png
• external/images/ui-icons_222222_256x240.png
• external/images/ui-icons_228ef1_256x240.png
• external/images/ui-icons_ef8c08_256x240.png
• external/images/ui-icons_ffd27a_256x240.png
• external/images/ui-icons_ffffff_256x240.png
• external/jquery.flot.min.js
• external/jquery-1.11.2.min.js
• external/jquery-2.1.3.min.js
• external/jquery-ui.min.css
• external/jquery-ui.min.js
• external/marked.js
• external/mathjax.js
• external/underscore-min.js
• gridworld_dp.html
• gridworld_td.html
• img/dpsolved.jpeg
• img/lambda.png
• img/policyiter.png
• img/qsa.jpeg
• img/sarsa.png
• img/traces.png
• index.html
• lib/rl.js
• loop.svg
• puckworld.html
• README.md
• waterworld.html
• waterworld.js

Public Handling Notes

• EXTRACTED: This page records public metadata and a source-grounded summary.
• INFERRED: Full local preservation, when available, is for private/local use unless a license or explicit source policy makes public redistribution safe.
• Do not treat this page as permission to republish unlicensed source text or code wholesale.