Methods › Reinforcement Learning › Policy Gradient Methods › MADDPG
MADDPG
Introduced by Ryan Lowe et al. in Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
MADDPG, or Multi-agent DDPG, extends DDPG into a multi-agent policy gradient algorithm where decentralized agents learn a centralized critic based on the observations and actions of all agents. It leads to learned policies that only use local information (i.e. their own observations) at execution time, does not assume a differentiable model of the environment dynamics or any particular structure on the communication method between agents, and is applicable not only to cooperative interaction but to competitive or mixed interaction involving both physical and communicative behavior. The critic is augmented with extra information about the policies of other agents, while the actor only has access to local information. After training is completed, only the local actors are used at execution phase, acting in a decentralized manner.
Papers archive 2025-07-28
30 shown of 36, 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.
-
Fully-Decentralized MADDPG with Networked Agents 9 Mar 2025 · 0 repositories · arXiv:2503.06747
-
Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization 8 Aug 2024 · 0 repositories · arXiv:2408.04251
-
An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning 10 May 2024 · 0 repositories · arXiv:2405.06161
-
Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing 18 Feb 2024 · 2 repositories · arXiv:2402.11653
-
Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chains 9 Dec 2023 · 0 repositories · arXiv:2312.05686
-
Adaptive Resource Management for Edge Network Slicing using Incremental Multi-Agent Deep Reinforcement Learning 26 Oct 2023 · 0 repositories · arXiv:2310.17523
-
Safe Hierarchical Reinforcement Learning for CubeSat Task Scheduling Based on Energy Consumption 21 Sep 2023 · 0 repositories · arXiv:2309.12004
-
Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit 8 Jun 2023 · 1 repository · arXiv:2306.05016
-
Reinforcement Learning With Reward Machines in Stochastic Games 27 May 2023 · 0 repositories · arXiv:2305.17372
-
Revisiting the Gumbel-Softmax in MADDPG 23 Feb 2023 · 1 repository · arXiv:2302.11793
-
On Multi-Agent Deep Deterministic Policy Gradients and their Explainability for SMARTS Environment 20 Jan 2023 · 0 repositories · arXiv:2301.09420
-
Multiagent Reinforcement Learning Based on Fusion-Multiactor-Attention-Critic for Multiple-Unmanned-Aerial-Vehicle Navigation Control 10 Oct 2022 · 1 repository
-
A New Approach to Training Multiple Cooperative Agents for Autonomous Driving 5 Sep 2022 · 0 repositories · arXiv:2209.02157
-
Two-Hop Age of Information Scheduling for Multi-UAV Assisted Mobile Edge Computing: FRL vs MADDPG 19 Jun 2022 · 0 repositories · arXiv:2206.09488
-
Balancing Profit, Risk, and Sustainability for Portfolio Management 6 Jun 2022 · 0 repositories · arXiv:2207.02134
-
MA-Dreamer: Coordination and communication through shared imagination 10 Apr 2022 · 0 repositories · arXiv:2204.04687
-
Decision-making of Emergent Incident based on P-MADDPG 19 Mar 2022 · 0 repositories · arXiv:2203.12673
-
Learning to Infer Belief Embedded Communication 15 Mar 2022 · 0 repositories · arXiv:2203.07832
-
Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method 31 Oct 2021 · 0 repositories · arXiv:2111.00438
-
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning 23 Sep 2021 · 11 repositories · arXiv:2109.11251Syntology ran 2 of 5 samples · 3 unverified
-
MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization 2 Sep 2021 · 1 repository · arXiv:2109.00882
-
A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization 13 Jul 2021 · 0 repositories · arXiv:2107.06115
-
Many Agent Reinforcement Learning Under Partial Observability 17 Jun 2021 · 0 repositories · arXiv:2106.09825
-
Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments 11 May 2021 · 0 repositories · arXiv:2105.04888
-
Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games 23 Nov 2020 · 0 repositories · arXiv:2011.11517
-
Human and Multi-Agent collaboration in a human-MARL teaming framework 12 Jun 2020 · 0 repositories · arXiv:2006.07301
-
Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning 19 May 2020 · 0 repositories · arXiv:2005.09453
-
Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward 24 Mar 2020 · 0 repositories · arXiv:2003.10598
-
Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning 23 Mar 2020 · 1 repository · arXiv:2003.10423Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
FACMAC: Factored Multi-Agent Centralised Policy Gradients 14 Mar 2020 · 3 repositories · arXiv:2003.06709Syntology ran 1 of 4 samples · 3 unverified
Tasks archive 2025-07-28
20 shown of 36 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