Pith. sign in

REVIEW 2 cited by

Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.17352 v2 pith:GTD7VV6P submitted 2023-05-27 cs.AI cs.LGcs.MA

classification cs.AIcs.LGcs.MA
keywords centralizedtrainingagentsdecentralizedexecutionframeworkagentctde
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Centralized Training with Decentralized Execution (CTDE) has recently emerged as a popular framework for cooperative Multi-Agent Reinforcement Learning (MARL), where agents can use additional global state information to guide training in a centralized way and make their own decisions only based on decentralized local policies. Despite the encouraging results achieved, CTDE makes an independence assumption on agent policies, which limits agents to adopt global cooperative information from each other during centralized training. Therefore, we argue that existing CTDE methods cannot fully utilize global information for training, leading to an inefficient joint-policy exploration and even suboptimal results. In this paper, we introduce a novel Centralized Advising and Decentralized Pruning (CADP) framework for multi-agent reinforcement learning, that not only enables an efficacious message exchange among agents during training but also guarantees the independent policies for execution. Firstly, CADP endows agents the explicit communication channel to seek and take advices from different agents for more centralized training. To further ensure the decentralized execution, we propose a smooth model pruning mechanism to progressively constraint the agent communication into a closed one without degradation in agent cooperation capability. Empirical evaluations on StarCraft II micromanagement and Google Research Football benchmarks demonstrate that the proposed framework achieves superior performance compared with the state-of-the-art counterparts. Our code will be made publicly available.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A feudal hierarchical MARL method where lower-level policies are rewarded with the upper level's advantage function, with theoretical alignment guarantees and strong benchmark results.

  2. Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A sparse action dependency graph derived from the coordination graph is sufficient for a locally optimal policy to be globally optimal in cooperative multi-agent RL.

Pith tools