Multi-Agent Distributed Deep Deterministic Policy Gradient for Partially Observable Tracking
In many existing multi-agent reinforcement learning tasks, each agent observes all the other agents from its own perspective. In addition, the training process is centralized, namely the critic of each agent can access the policies of all the agents. This scheme has certain limitations since every s...
Main Authors: | Dongyu Fan, Haikuo Shen, Lijing Dong |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Actuators |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-0825/10/10/268 |
Similar Items
-
Attitude Control of Stabilized Platform Based on Deep Deterministic Policy Gradient with Disturbance Observer
by: Aiqing Huo, et al.
Published: (2023-11-01) -
Scalable and Transferable Reinforcement Learning for Multi-Agent Mixed Cooperative–Competitive Environments Based on Hierarchical Graph Attention
by: Yining Chen, et al.
Published: (2022-04-01) -
Improved Multi-Agent Deep Deterministic Policy Gradient for Path Planning-Based Crowd Simulation
by: Shangfei Zheng, et al.
Published: (2019-01-01) -
Research on Wargame Decision-Making Method Based on Multi-Agent Deep Deterministic Policy Gradient
by: Sheng Yu, et al.
Published: (2023-04-01) -
Stability Analysis of Multi-Agent Tracking Systems with Quasi-Cyclic Switching Topologies
by: Dongyu Fan, et al.
Published: (2020-12-01)