Papers › Value-Decomposition Networks For Cooperative Multi-Agent Learning

Value-Decomposition Networks For Cooperative Multi-Agent Learning

16 Jun 2017arXiv:1706.05296archive 2025-07-28

Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z. Leibo, Karl Tuyls, Thore Graepel

We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and decentralized approaches, we find the problem of spurious rewards and a phenomenon we call the "lazy agent" problem, which arises due to partial observability. We address these problems by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions. We perform an experimental evaluation across a range of partially-observable multi-agent domains and show that learning such value-decompositions leads to superior results, in particular when combined with weight sharing, role information and information channels.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

Louiii/ValueDecomposition mentioned on GitHubSyntology: not harvested report
TonghanWang/DOP mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv:1803.11485; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
TonghanWang/NDQ mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv:1803.11485; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
cathyhxh/ctds mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/benchmarl mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BenchMARL: Benchmarking Multi-Agent Reinforcement Learning (arXiv:2312.01472; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hhhusiyi-monash/UPDeT mentioned on GitHubpytorchSyntology: not harvested report
jjbong/strangeness_exploration mentioned on GitHubpytorchSyntology: not harvested report
jugg1er/air mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
puyuan1996/MARL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv:1803.11485; that paper's own run record: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
tjuhaoxiaotian/pymarl3 mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-agent Reinforcement LearningReinforcement LearningReinforcement Learning (RL)SMAC+reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
SMAC+ Def_Armored_parallel VDN Median Win Rate 5.0 #5 of 10 Archive leaderboard report
SMAC+ Def_Armored_sequential VDN Median Win Rate 96.9 #2 of 11 Archive leaderboard report
SMAC+ Def_Infantry_parallel VDN Median Win Rate 95.0 #4 of 10 Archive leaderboard report
SMAC+ Def_Infantry_sequential VDN Median Win Rate 96.9 #6 of 11 Archive leaderboard report
SMAC+ Def_Outnumbered_parallel VDN Median Win Rate 0.0 #8 of 10 Archive leaderboard report
SMAC+ Def_Outnumbered_sequential VDN Median Win Rate 15.6 #4 of 11 Archive leaderboard report
SMAC+ Off_Complicated_parallel VDN Median Win Rate 70.0 #2 of 10 Archive leaderboard report
SMAC+ Off_Distant_parallel VDN Median Win Rate 85.0 #2 of 10 Archive leaderboard report
SMAC+ Off_Hard_parallel VDN Median Win Rate 15.0 #2 of 10 Archive leaderboard report
SMAC+ Off_Near_parallel VDN Median Win Rate 90.0 #3 of 10 Archive leaderboard report
SMAC+ Off_Superhard_parallel VDN Median Win Rate 0.0 #6 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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