---
title: 'Proximal Policy Optimization Algorithms'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-11); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/1707-06347-ppo.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov, Proximal Policy Optimization Algorithms (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-11.'
category: arxiv
topic_area: 'ai-research: foundations'
tags: arxiv, reinforcement-learning, ppo, foundations
arxiv_id: 1707.06347
alias: 1707.06347-ppo
type: pointer
format: pointer
sources:
  - id: S1
    title: 'Proximal Policy Optimization Algorithms'
    publisher: arXiv
    authors: 'John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov'
    url: https://arxiv.org/abs/1707.06347
    version_read: 'v2 (28 Aug 2017)'
    accessed: 2026-11-11
    license: 'arXiv non-exclusive distribution license'
---
# Proximal Policy Optimization Algorithms

## Summary
[Proximal Policy Optimization Algorithms](https://arxiv.org/abs/1707.06347) (2017) introduced PPO, a policy-gradient algorithm that is still the workhorse behind much of RLHF and later reasoning-model training. It aimed to get much of the reliability of earlier trust-region methods with a simpler, more practical update.

What it introduced: the PPO clipped (and related) objectives for updating a policy without taking steps that are too large, along with a practical training algorithm that became a default in deep RL.

What it led to: the usual optimizer in early RLHF pipelines, including InstructGPT, and a baseline later papers still compare against even when they replace PPO with other preference methods. Live notes: [2204-05862-helpful-harmless-rlhf](https://iinventedlight.com/library/notes/2204-05862-helpful-harmless-rlhf/) and [2305-18290-direct-preference-optimization](https://iinventedlight.com/library/notes/2305-18290-direct-preference-optimization/). See also this batch's pointer to deep RL from human preferences.

Where to read it: https://arxiv.org/abs/1707.06347 (v2, last revised 28 Aug 2017).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).