Papers › ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

29 Nov 2022arXiv:2211.16068archive 2025-07-28

Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policies at the same time. Starting from first principle, in this paper, we manage to solve the non-stationarity problem by proposing bidirectional action-dependent Q-learning (ACE). Central to the development of ACE is the sequential decision-making process wherein only one agent is allowed to take action at one time. Within this process, each agent maximizes its value function given the actions taken by the preceding agents at the inference stage. In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action. Given the design of bidirectional dependency, ACE effectively turns a multiagent MDP into a single-agent MDP. We implement the ACE framework by identifying the proper network representation to formulate the action dependency, so that the sequential decision process is computed implicitly in one forward pass. To validate ACE, we compare it with strong baselines on two MARL benchmarks. Empirical experiments demonstrate that ACE outperforms the state-of-the-art algorithms on Google Research Football and StarCraft Multi-Agent Challenge by a large margin. In particular, on SMAC tasks, ACE achieves 100% success rate on almost all the hard and super-hard maps. We further study extensive research problems regarding ACE, including extension, generalization, and practicability. Code is made available to facilitate further research.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2211.16068")

Code

Syntology Ran 0 of 4 code samples harvested from 1 repository linked to this paper; 4 have no recorded run.

By repository: official repository: 4 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

opendilab/ace officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4unverified

Licence: 0 of the 4 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 opendilab/ace. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

ActionSampler opendilab/ace/ding/model/template/grf_ace.py official repository unverified Apache-2.0 (permissive) · ab128bc8ab5f6d4a · report
concat_state_action_pairs opendilab/ace/ding/reward_model/gail_irl_model.py official repository unverified Apache-2.0 (permissive) · e1b90070a1e51736 · report
pfsp opendilab/ace/ding/league/algorithm.py official repository unverified Apache-2.0 (permissive) · a074649f8b341a8a · report
uniform opendilab/ace/ding/league/algorithm.py official repository unverified Apache-2.0 (permissive) · c7dde4c97b7136b3 · report

Tasks

Decision MakingMulti-agent Reinforcement LearningQ-LearningSMACSMAC+Sequential Decision MakingStarcraft

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
SMAC SMAC 3s5z_vs_3s6z ACE Median Win Rate 100 #1 of 13 Archive leaderboard report
SMAC SMAC 6h_vs_8z ACE Median Win Rate 93.75 #1 of 14 Archive leaderboard report
SMAC SMAC MMM2 ACE Median Win Rate 100 #1 of 14 Archive leaderboard report
SMAC SMAC corridor ACE Median Win Rate 100 #1 of 13 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.

Methods

1x1 ConvolutionAdamBatch NormalizationBigGANConditional Batch NormalizationConvolutionDense ConnectionsEarly StoppingFeedforward NetworkGAN Hinge LossLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationProjection DiscriminatorQ-LearningReLUResidual BlockResidual ConnectionSAGANSoftmaxSpectral NormalizationTTURTruncation Trick

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