Multi-agent reinforcement learning with directed exploration and selective memory reuse

Jiang, Shuo; Amato, Christopher

doi:10.1145/3412841.3441953

Cited by 12 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The single-agent scenario did not fully reflect the advantages of the multi-agent algorithm, so we conducted comparative experiments in a more complex multi-agent environment with composite actions. Using the toy multi-agents reinforcementlearning problems designed by Jiang et al [43], the action space was also complex, and the agent needed to decide future multi-step actions one time. MADDPG was a distributed algorithm.…”

Section: A Comparative Experiment: the Effect Of Splitting Composite ...mentioning

confidence: 99%

A Sequential Decision Algorithm of Reinforcement Learning for Composite Action Space

Gao,

Wang,

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

It is the key research object of electronic warfare to use UAV( Unmanned Aerial Vehicle) clusters to carry out electronic countermeasure tasks. The UAV carries loads such as reconnaissance and interference at the same time, which makes it necessary to simultaneously decide multiple types of actions-namely, compound actions-which poses a challenge to intelligent decision-making algorithms.Considering the problem of action-space dimensional complexity and weak collaboration between decisions in multi-agent scenarios with composite actions, this study proposed a decision algorithm involving a multiagent reinforcement-learning sequence, which combined joint composite actions into sequential decision, reducing the difficulty of a single decision and enhancing the collaboration between various agents and their individual decisions. Because long decision sequences required better depth modeling and had high variance, a DeLighT module was added to the naïve transformer model to increase the depth and baseline techniques, which were used to reduce the variance in the value estimation. The simulated results verified the effectiveness of the proposed algorithm in the UAV cooperative combat scenario, where each agent had a composite action space and showed better performance than the existing algorithms.

show abstract

Section: A Comparative Experiment: the Effect Of Splitting Composite ...mentioning

confidence: 99%

A Sequential Decision Algorithm of Reinforcement Learning for Composite Action Space

Gao,

Wang,

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…GhostRun environment is a cooperative multi-agent game adapted from Jiang et al 2021 (Jiang and Amato (2021)). GhostRun environment consists of multiple agents with partial view of a 2D…”

Section: A Appendixmentioning

confidence: 99%

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

Liu¹,

Shah²,

Boussif³

et al. 2022

Preprint

View full text Add to dashboard Cite

In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.Preprint. Under review.

show abstract

VMAS: A Vectorized Multi-agent Simulator for Collective Robot Learning

Bettini,

Kortvelesy,

Blumenkamp

et al. 2024

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

Multi-agent reinforcement learning with directed exploration and selective memory reuse

Cited by 12 publications

References 15 publications

A Sequential Decision Algorithm of Reinforcement Learning for Composite Action Space

A Sequential Decision Algorithm of Reinforcement Learning for Composite Action Space

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

VMAS: A Vectorized Multi-agent Simulator for Collective Robot Learning

Contact Info

Product

Resources

About