Methods › Reinforcement Learning › Distributed Reinforcement Learning › DD-PPO
Decentralized Distributed Proximal Policy Optimization
DD-PPO
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).
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems 6 May 2025 · 0 repositories · arXiv:2505.03946
-
Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks 18 May 2023 · 2 repositories · arXiv:2305.10997
-
Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation 17 Dec 2022 · 1 repository · arXiv:2212.08801
-
VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement 11 Oct 2022 · 1 repository · arXiv:2210.05064
-
Uncertainty-driven Planner for Exploration and Navigation 24 Feb 2022 · 1 repository · arXiv:2202.11907
-
Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents 7 Sep 2020 · 0 repositories · arXiv:2009.03231
-
Auxiliary Tasks Speed Up Learning PointGoal Navigation 9 Jul 2020 · 1 repository · arXiv:2007.04561Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames 1 Nov 2019 · 8 repositories · arXiv:1911.00357
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.
Usage over time archive 2025-07-28
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
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