Methods › Reinforcement Learning › Distributed Reinforcement Learning › DD-PPO

Decentralized Distributed Proximal Policy Optimization

DD-PPO

8 papers tagged archive 2025-07-28

Introduced by Erik Wijmans et al. in DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Decentralized Distributed Proximal Policy Optimization (DD-PPO) is a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever `stale'), making it conceptually simple and easy to implement.

Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable performance of TRPO, while using only first-order optimization.

Let rₜ(θ) denote the probability ratio rₜ(θ) = (π_θ(aₜ|sₜ))/(π_(θ_(old))(aₜ|sₜ)), so r(θ_(old)) = 1. TRPO maximizes a “surrogate” objective:

Lᵛ(θ) = 𝔼̂ₜ[(π_θ(aₜ|sₜ))/(π_(θ_(old))(aₜ|sₜ)))Âₜ] = 𝔼̂ₜ[rₜ(θ)Âₜ]

As a general abstraction, DD-PPO implements the following: at step k, worker n has a copy of the parameters, θᵏₙ, calculates the gradient, δθᵏₙ, and updates θ via

θᵏ⁺¹ₙ = ParamUpdate(θᵏₙ, AllReduce(δθᵏ₁, …, δθᵏ_N)) = ParamUpdate(θᵏₙ, 1/N ∑ᵢ₌₁ᴺ δθᵏᵢ )

where ParamUpdate is any first-order optimization technique (e.g. gradient descent) and AllReduce performs a reduction (e.g. mean) over all copies of a variable and returns the result to all workers. Distributed DataParallel scales very well (near-linear scaling up to 32,000 GPUs), and is reasonably simple to implement (all workers synchronously running identical code).

PaperSource

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames” (arXiv:1911.00357, 663 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:1911.00357: its page on this site · ask the lookup about it.

Near matches the lookup lists, each a different name: CADDTO-PPO.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 8 · with a code link: 6 · where Syntology ran a sample: 1 (0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 8 tagged: 0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 8 of 8, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Navigate4
PointGoal Navigation4
GPU3
Reinforcement Learning3
Reinforcement Learning (RL)2
Robot Navigation2
reinforcement-learning2
Autonomous Navigation1
Deep Reinforcement Learning1
Lifelong learning1
ObjectGoal Navigation1
Out-of-Distribution Generalization1
Problem Decomposition1
Scene Understanding1
Scheduling1
Semantic Segmentation1
Visual Odometry1
model1

Usage over time archive 2025-07-28

Papers per year tagged with DD-PPO: 2019 to 2025, peak 3 3 0 2019: 1 paper 2019 2020: 2 papers 2020 2021: 0 papers 2021 2022: 3 papers 2022 2023: 1 paper 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (8 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Distributed Reinforcement Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections