Papers › WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

31 Aug 2021arXiv:2108.13976archive 2025-07-28

Tian Lan, Sunil Srinivasa, Huan Wang, Stephan Zheng

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In particular, there are key system engineering bottlenecks when using RL in complex environments that feature multiple agents with high-dimensional state, observation, or action spaces. We present WarpDrive, a flexible, lightweight, and easy-to-use open-source RL framework that implements end-to-end deep multi-agent RL on a single GPU (Graphics Processing Unit), built on PyCUDA and PyTorch. Using the extreme parallelization capability of GPUs, WarpDrive enables orders-of-magnitude faster RL compared to common implementations that blend CPU simulations and GPU models. Our design runs simulations and the agents in each simulation in parallel. It eliminates data copying between CPU and GPU. It also uses a single simulation data store on the GPU that is safely updated in-place. WarpDrive provides a lightweight Python interface and flexible environment wrappers that are easy to use and extend. Together, this allows the user to easily run thousands of concurrent multi-agent simulations and train on extremely large batches of experience. Through extensive experiments, we verify that WarpDrive provides high-throughput and scales almost linearly to many agents and parallel environments. For example, WarpDrive yields 2.9 million environment steps/second with 2000 environments and 1000 agents (at least 100x higher throughput compared to a CPU implementation) in a benchmark Tag simulation. As such, WarpDrive is a fast and extensible multi-agent RL platform to significantly accelerate research and development.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

salesforce/warp-drive officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mila-iqia/climate-cooperation-competition mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
salesforce/ai-economist mentioned on GitHubBSD-3-ClauseSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

salesforce/warp-drive official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
dynamic_import warp_drive/training/models/factory.py ran BSD-3-Clause (permissive) · 9c61b6cc4b60d9af · report fixture: signature model_name:str/0/str, model_pool:dict/0/? · returned type · level recorded 2026-09-25
generate_random_actions warp_drive/env_cpu_gpu_consistency_checker.py ran BSD-3-Clause (permissive) · 443d55b2bf005c50 · report fixture: signature env:MockEnv/0/?, num_envs:int/0/int, seed:int/0/int · returned list · level recorded 2026-09-26
salesforce/ai-economist community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
cfg_dict_from_yaml ai_economist/real_business_cycle/experiment_utils.py ran BSD-3-Clause (permissive) · d8a1bc0618312f77 · report fixture: signature hparams_path:PosixPath/0/?, consumption_choices:ndarray/1/float, work_choices:ndarray/1/float, price_and_wage:ndarray/1/float, tax_choices:ndarray/1/float, group_name:str/0/str · returned dict · level recorded 2026-09-25
check_if_ep_str_policy_exists ai_economist/real_business_cycle/train_bestresponse.py ran BSD-3-Clause (permissive) · 6a2b7a164a3d1480 · report fixture: signature rollout_path:PosixPath/0/?, ep_str:str/0/str · returned bool · level recorded 2026-09-25
hash_from_dict ai_economist/real_business_cycle/experiment_utils.py ran BSD-3-Clause (permissive) · 580e9b27b830eb25 · report fixture: signature d:dict/0/? · returned int · level recorded 2026-09-25
recursive_obs_dict_to_spaces_dict ai_economist/foundation/env_wrapper.py ran BSD-3-Clause (permissive) · a5f97a16853000a0 · report fixture: signature obs:dict/0/? · returned Dict · level recorded 2026-09-25
seed_from_base_seed ai_economist/real_business_cycle/experiment_utils.py ran fingerprinted BSD-3-Clause (permissive) · 799c662498b9093c · report fixture: signature base_seed:int/0/int · returned int · level recorded 2026-09-25

Tasks

Decision MakingDeep Reinforcement LearningMulti-agent Reinforcement LearningReinforcement Learning (RL)TAG

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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