CN116775220A - Distributed simulation optimization method, system, equipment and medium based on asynchronous process - Google Patents
Distributed simulation optimization method, system, equipment and medium based on asynchronous process Download PDFInfo
- Publication number
- CN116775220A CN116775220A CN202310803130.8A CN202310803130A CN116775220A CN 116775220 A CN116775220 A CN 116775220A CN 202310803130 A CN202310803130 A CN 202310803130A CN 116775220 A CN116775220 A CN 116775220A
- Authority
- CN
- China
- Prior art keywords
- agent
- simulation
- agents
- distributed
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 97
- 230000008569 process Effects 0.000 title claims abstract description 59
- 238000005457 optimization Methods 0.000 title claims abstract description 25
- 230000002452 interceptive effect Effects 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 9
- 230000008901 benefit Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Multi Processors (AREA)
Abstract
The invention provides a distributed simulation optimization method, a system, equipment and a medium based on an asynchronous process, wherein the method comprises the following steps: responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, and creating and managing a plurality of sub intelligent agents by the main intelligent agent according to self decision attributes; invoking a ray distributed computing component, submitting agents to a distributed cluster, and distributing each agent to run in a corresponding single process of a multi-server; creating a simulation database, and performing interactive feedback between the intelligent agents through the simulation database: and calling an asynchronous programming component to configure the agents, and managing a plurality of agents scattered in different processes through an asynchronous process model. According to the invention, more agents are created and managed through a distributed computing technology, the scale of the multi-agent simulation model is expanded, and the distributed agents are managed through an asynchronous technology, so that the simulation model operates more stably and efficiently.
Description
Technical Field
The invention relates to the technical field of distributed simulation, in particular to a distributed simulation optimization method, system, equipment and medium based on an asynchronous process.
Background
The existing simulation technology refers to the fact that an intrinsic process occurring in a system is reproduced by using a model, the existing or designed system is researched through experiments on a system model, simulation elements corresponding to each real simulation object in the simulation technology are required to be depicted in a simulation environment by multiple agents, each agent has independent attributes and decision behaviors, and the agents are fed back interactively in the simulation environment;
however, the existing multi-agent simulation technology has the following defects:
(1) Generating a plurality of agents through a single main process, wherein the essence is still calculation in one process, the number of the simulative agents is limited, and the performance of multi-core parallel calculation of a computer cannot be effectively utilized;
(2) The simulation system needs to repeatedly call data and components to complete interactive feedback of the simulation process, and when the number of the agents reaches a certain threshold, concurrent access in the simulation model cannot be processed, so that the universality and the performance are poor.
(3) Under the multi-agent simulation model, for events with longer time consumption, the synchronous multi-process mode is easy to block program execution flow, and the states of agents in the multi-process cannot be effectively managed.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a distributed simulation optimization method, a system, equipment and a storage medium based on an asynchronous process, which can be realized.
The invention discloses a distributed simulation optimization method based on an asynchronous process, which comprises the following steps:
s1: responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, wherein the main intelligent agent creates and manages a plurality of sub intelligent agents according to self decision attributes;
s2: invoking a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to run in a corresponding single process of a multi-server;
s3: creating a simulation database, accessing the main agent and the sub agents into the simulation database, and performing interactive feedback among the agents through the simulation database;
s4: and calling an asynchronous programming component to configure the intelligent agent, and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
In an alternative embodiment, the creating an agent designs the agent into classes through programming, the classes are in one-to-one correspondence with the agent, the classes include attributes and methods, the attributes of the classes correspond to state information of the agent, and the methods correspond to decision information of the agent.
In an alternative embodiment, said creating a master agent for managing a global simulation environment in response to a user instruction further comprises:
s101, creating a simulation environment according to a user instruction, wherein the simulation environment comprises environment information, and the intelligent agent executes self-decision by reading the environment information and other intelligent agent information.
In an optional embodiment, the Ray distributed computing component is a computing framework of a simulation model, the intelligent agent is accessed to a distributed computing interface after being marked by the Ray distributed computing component after being created, the intelligent agent distributes distributed computing cluster resources to the Ray distributed computing component, and simulation computation is completed by the distributed computing clusters when decision is executed.
In an alternative embodiment, the asynchronous programming component asynchronously marks the agents when they are created, and the master agent manages the decision-making behavior of the child agents by a select/pool method in the operating system.
In an optional embodiment, in the asynchronous process model, the operating system feeds back the update information of the sub-agent to the main agent, the main agent manages the sub-agent to pull the state information and decision information of other sub-agents and report the state information and decision information of the sub-agent to the simulation database, the main agent pulls the global information in the simulation database, performs decision management on the sub-agent, and completes the update of the agent information calculated by the simulation in turn.
In an optional embodiment, the simulation database comprises MySQL and Redis databases, and the information interaction between the agents pulls state information and decision information of other agents through the simulation database and reports the state information and the decision information of the agents.
The second aspect of the invention discloses a distributed simulation optimization system based on an asynchronous process, which comprises:
the intelligent agent generation module is used for responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, and creating and managing a plurality of sub intelligent agents according to self decision attributes by the main intelligent agent;
the distributed computing module is used for calling a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to a corresponding single process of a multi-server for operation;
the data interaction module is used for creating a simulation database, accessing the main intelligent agent and the sub intelligent agents into the simulation database, and carrying out interaction feedback among the intelligent agents through the simulation database;
and the asynchronous management module is used for calling the asynchronous programming component to configure the intelligent agent and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
The third aspect of the invention discloses a distributed simulation optimizing device based on an asynchronous process, which comprises:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the asynchronous process based distributed simulation optimization method as disclosed in any of the first aspects of the present invention.
A fourth aspect of the present invention discloses a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the asynchronous process-based distributed simulation optimization method according to any one of the first aspects of the present invention.
Compared with the prior art, the invention has the following advantages:
(1) According to the invention, more intelligent agents can be created and managed through a distributed computing technology, a larger-scale multi-intelligent-agent simulation model is realized, and the intelligent agents are sent to a distributed computing cluster formed by a plurality of servers, so that the advantage of distributed parallel computing of a modern computer is exerted;
(2) According to the method, the loading of the intelligent agents scattered on the plurality of servers is managed through an asynchronous thread technology, so that the operation of the multi-intelligent-agent simulation model is more stable and efficient;
(3) According to the invention, the interactive feedback among multiple agents is realized by using the database middleware such as MySQL, redis and the like, the main agent serving as global management can realize global maintenance and update of the simulation model without finishing polling of all sub agents, a response interface of polling action is not required to be increased, network overhead is reduced, and the simulation system is simplified and has high stability.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of a distributed simulation optimization method based on an asynchronous process of the present invention;
FIG. 2 is a schematic diagram of a distributed simulation optimization system based on an asynchronous process of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," "fourth," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, the embodiment of the invention discloses a distributed simulation optimization method based on an asynchronous process, which comprises the following steps:
s1: responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, wherein the main intelligent agent creates and manages a plurality of sub intelligent agents according to self decision attributes;
s2: invoking a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to run in a corresponding single process of a multi-server;
s3: creating a simulation database, accessing the main agent and the sub agents into the simulation database, and performing interactive feedback among the agents through the simulation database;
s4: and calling an asynchronous programming component to configure the intelligent agent, and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
In an alternative embodiment, the creating an agent designs the agent into classes through programming, the classes are in one-to-one correspondence with the agent, the classes include attributes and methods, the attributes of the classes correspond to state information of the agent, and the methods correspond to decision information of the agent.
In an alternative embodiment, said creating a master agent for managing a global simulation environment in response to a user instruction further comprises:
s101, creating a simulation environment according to a user instruction, wherein the simulation environment comprises environment information, and the intelligent agent executes self-decision by reading the environment information and other intelligent agent information.
In an optional embodiment, the Ray distributed computing component is a computing framework of a simulation model, the intelligent agent is accessed to a distributed computing interface after being marked by the Ray distributed computing component after being created, the intelligent agent distributes distributed computing cluster resources to the Ray distributed computing component, and simulation computation is completed by the distributed computing clusters when decision is executed.
In an alternative embodiment, the asynchronous programming component asynchronously marks the agents when they are created, and the master agent manages the decision-making behavior of the child agents by a select/pool method in the operating system.
In the asynchronous model, if the state of the sub-agent is updated, the main agent (manager) is actively notified by the select/pool method of the operating system, and if the state of the sub-agent is not updated, the main agent enters a waiting state. Accordingly, the agent 1 (manager) can query or update the status information of other agents, and can manage the status of very many agents because the select/pool method of the operating system is used instead of polling, if the synchronization model is used, the main agent (manager) needs to poll the status of the sub-agents, and the sub-agents also need to add a corresponding response interface to this polling action, which increases network overhead in an intangible way, and makes the system more complex, which means unstable.
In an optional embodiment, in the asynchronous process model, the operating system feeds back the update information of the sub-agent to the main agent, the main agent manages the sub-agent to pull the state information and decision information of other sub-agents and report the state information and decision information of the sub-agent to the simulation database, the main agent pulls the global information in the simulation database, performs decision management on the sub-agent, and completes the update of the agent information calculated by the simulation in turn.
It should be noted that, in a simulation environment, n agents are provided, each agent simulates an object in the real world, each agent needs to acquire information of other agents and simulation environment information in the simulation process, so that a decision at the current moment can be made, after the agents make the decision, decision information of the agents can be transmitted to other agents, so that a complete interactive feedback is formed, for example, in the simulation of picking a warehouse, the agents can be pickers, before picking, each picker needs to make a picking decision according to own information (which commodities need to be picked), other agent information systems (tasks to which other pickers are allocated), environment information (distribution of commodities on a shelf), and the like. When the picking worker completes picking, the picking worker needs to inform other workers of the picking state of the picking worker to perform the next round of picking.
It should be noted that each agent is an independent individual, and is independent of each other and is related through information interaction. Thus, in computer programming, each agent may be run in a separate server process, and information interaction between agents may be accomplished through middleware such as databases.
In an optional embodiment, the simulation database comprises MySQL and Redis databases, and the information interaction between the agents pulls state information and decision information of other agents through the simulation database and reports the state information and the decision information of the agents.
It should be noted that, through the database, the agents distributed in different server processes can interact, each agent reports its own decision state, and queries the state information of other agents, thereby forming a multi-agent simulation system which cooperates and contacts with each other.
The invention has the following advantages:
(1) According to the invention, more intelligent agents can be created and managed through a distributed computing technology, a larger-scale multi-intelligent-agent simulation model is realized, and the intelligent agents are sent to a distributed computing cluster formed by a plurality of servers, so that the advantage of distributed parallel computing of a modern computer is exerted;
(2) According to the method, the loading of the intelligent agents scattered on the plurality of servers is managed through an asynchronous thread technology, so that the operation of the multi-intelligent-agent simulation model is more stable and efficient;
(3) According to the invention, the interactive feedback among multiple agents is realized by using the database middleware such as MySQL, redis and the like, the main agent serving as global management can realize global maintenance and update of the simulation model without finishing polling of all sub agents, a response interface of polling action is not required to be increased, network overhead is reduced, and the simulation system is simplified and has high stability.
As shown in FIG. 2, a second aspect of the present invention discloses a distributed simulation optimization system based on an asynchronous process, the system comprising:
the intelligent agent generation module is used for responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, and creating and managing a plurality of sub intelligent agents according to self decision attributes by the main intelligent agent;
the distributed computing module is used for calling a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to a corresponding single process of a multi-server for operation;
the data interaction module is used for creating a simulation database, accessing the main intelligent agent and the sub intelligent agents into the simulation database, and carrying out interaction feedback among the intelligent agents through the simulation database;
and the asynchronous management module is used for calling the asynchronous programming component to configure the intelligent agent and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
The third aspect of the invention discloses a distributed simulation optimizing device based on an asynchronous process, which comprises:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the asynchronous process based distributed simulation optimization method as disclosed in any of the first aspects of the present invention.
A fourth aspect of the present invention discloses a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the asynchronous process-based distributed simulation optimization method according to any one of the first aspects of the present invention.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A distributed simulation optimization method based on an asynchronous process, the method comprising:
s1: responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, wherein the main intelligent agent creates and manages a plurality of sub intelligent agents according to self decision attributes;
s2: invoking a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to run in a corresponding single process of a multi-server;
s3: creating a simulation database, accessing the main agent and the sub agents into the simulation database, and performing interactive feedback among the agents through the simulation database;
s4: and calling an asynchronous programming component to configure the intelligent agent, and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
2. The asynchronous process-based distributed simulation optimization method according to claim 1, wherein the creating an agent designs the agent into classes by programming, wherein the classes are in one-to-one correspondence with the agent, the classes comprise attributes and methods, the attributes of the classes correspond to state information of the agent, and the methods correspond to decision information of the agent.
3. The asynchronous process based distributed simulation optimization method of claim 1, wherein the creating a master agent for managing a global simulation environment in response to a user instruction further comprises:
s101, creating a simulation environment according to a user instruction, wherein the simulation environment comprises environment information, and the intelligent agent executes self-decision by reading the environment information and other intelligent agent information.
4. The distributed simulation optimization method based on the asynchronous process according to claim 1, wherein the Ray distributed computing component is a computing framework of a simulation model, the intelligent agent is accessed to a distributed computing interface after being marked by the Ray distributed computing component after being created, the intelligent agent distributes distributed computing cluster resources to the Ray distributed computing component, and simulation computation is completed through the distributed computing clusters when decision is executed.
5. The asynchronous process-based distributed simulation optimization method of claim 1, wherein the asynchronous programming component asynchronously marks when creating the agent, and the main agent manages decision behaviors of the sub agents through a select/pool method in an operating system.
6. The asynchronous process-based distributed simulation optimization method according to claim 5, wherein in the asynchronous process model, the operating system feeds back the sub-agent update information to the main agent, the main agent manages the sub-agent to pull state information and decision information of other sub-agents and reports the state information and decision information of the main agent to the simulation database, the main agent pulls global information in the simulation database, performs decision management on the sub-agents, and completes the update of the agent information of the current round of simulation calculation.
7. The distributed simulation optimization method based on the asynchronous process according to claim 1, wherein the simulation database comprises a MySQL database and a Redis database, and the information interaction between the agents pulls state information and decision information of other agents through the simulation database and reports the state information and the decision information of the agents.
8. A distributed simulation optimization system based on an asynchronous process, the system comprising:
the intelligent agent generation module is used for responding to a user instruction, creating a main intelligent agent for managing a global simulation environment, and creating and managing a plurality of sub intelligent agents according to self decision attributes by the main intelligent agent;
the distributed computing module is used for calling a ray distributed computing component, submitting the agents to a distributed cluster, and distributing each agent to a corresponding single process of a multi-server for operation;
the data interaction module is used for creating a simulation database, accessing the main intelligent agent and the sub intelligent agents into the simulation database, and carrying out interaction feedback among the intelligent agents through the simulation database;
and the asynchronous management module is used for calling the asynchronous programming component to configure the intelligent agent and managing a plurality of intelligent agents scattered in different processes through an asynchronous process model.
9. A distributed simulation optimizing device based on an asynchronous process, comprising:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the asynchronous process based distributed simulation optimization method of any of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform the asynchronous process-based distributed simulation optimization method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310803130.8A CN116775220B (en) | 2023-06-30 | 2023-06-30 | Distributed simulation optimization method, system, equipment and medium based on asynchronous process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310803130.8A CN116775220B (en) | 2023-06-30 | 2023-06-30 | Distributed simulation optimization method, system, equipment and medium based on asynchronous process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116775220A true CN116775220A (en) | 2023-09-19 |
| CN116775220B CN116775220B (en) | 2024-04-12 |
Family
ID=88009774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310803130.8A Active CN116775220B (en) | 2023-06-30 | 2023-06-30 | Distributed simulation optimization method, system, equipment and medium based on asynchronous process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116775220B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130080358A1 (en) * | 2011-09-28 | 2013-03-28 | Causata Inc. | Online asynchronous reinforcement learning from concurrent customer histories |
| CN110266771A (en) * | 2019-05-30 | 2019-09-20 | 天津神兔未来科技有限公司 | Distributed intelligence node and distributed swarm intelligence system dispositions method |
| US20200143208A1 (en) * | 2018-11-05 | 2020-05-07 | Royal Bank Of Canada | Opponent modeling with asynchronous methods in deep rl |
| CN112784445A (en) * | 2021-03-11 | 2021-05-11 | 四川大学 | Parallel distributed computing system and method for flight control agent |
| CN113836754A (en) * | 2021-11-26 | 2021-12-24 | 湖南高至科技有限公司 | Multi-agent simulation modeling oriented simulation method, device, equipment and medium |
| CN114330651A (en) * | 2021-12-14 | 2022-04-12 | 中国运载火箭技术研究院 | Layered multi-agent reinforcement learning method oriented to multi-element joint instruction control |
| CN115099124A (en) * | 2022-05-20 | 2022-09-23 | 北京仿真中心 | Multi-agent distribution collaborative training simulation method |
| CN115167217A (en) * | 2022-07-20 | 2022-10-11 | 上海交通大学 | Multi-agent cooperative control method and medium based on hybrid triggering mechanism |
| CN116205288A (en) * | 2023-03-21 | 2023-06-02 | 国网智能电网研究院有限公司 | Reinforced learning architecture and reinforced learning architecture model parameter copying method |
| CN116226662A (en) * | 2023-01-05 | 2023-06-06 | 哈尔滨工业大学（深圳） | Multi-agent collaborative reinforcement learning method, terminal and storage medium |
-
2023
- 2023-06-30 CN CN202310803130.8A patent/CN116775220B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130080358A1 (en) * | 2011-09-28 | 2013-03-28 | Causata Inc. | Online asynchronous reinforcement learning from concurrent customer histories |
| US20200143208A1 (en) * | 2018-11-05 | 2020-05-07 | Royal Bank Of Canada | Opponent modeling with asynchronous methods in deep rl |
| CN110266771A (en) * | 2019-05-30 | 2019-09-20 | 天津神兔未来科技有限公司 | Distributed intelligence node and distributed swarm intelligence system dispositions method |
| CN112784445A (en) * | 2021-03-11 | 2021-05-11 | 四川大学 | Parallel distributed computing system and method for flight control agent |
| CN113836754A (en) * | 2021-11-26 | 2021-12-24 | 湖南高至科技有限公司 | Multi-agent simulation modeling oriented simulation method, device, equipment and medium |
| CN114330651A (en) * | 2021-12-14 | 2022-04-12 | 中国运载火箭技术研究院 | Layered multi-agent reinforcement learning method oriented to multi-element joint instruction control |
| CN115099124A (en) * | 2022-05-20 | 2022-09-23 | 北京仿真中心 | Multi-agent distribution collaborative training simulation method |
| CN115167217A (en) * | 2022-07-20 | 2022-10-11 | 上海交通大学 | Multi-agent cooperative control method and medium based on hybrid triggering mechanism |
| CN116226662A (en) * | 2023-01-05 | 2023-06-06 | 哈尔滨工业大学（深圳） | Multi-agent collaborative reinforcement learning method, terminal and storage medium |
| CN116205288A (en) * | 2023-03-21 | 2023-06-02 | 国网智能电网研究院有限公司 | Reinforced learning architecture and reinforced learning architecture model parameter copying method |
Non-Patent Citations (3)
| Title |
|---|
| QIYUE YIN等: "Distributed Deep Reinforcement Learning：A Survey and A Multi-Player Multi-Agent Learning Toolbox", 《ARXIV.ORG》, pages 1 - 14 * |
| 张晶等: "A3C深度强化学习模型压缩及知识抽取", 《计算机研究与发展》, vol. 60, no. 06, pages 1373 - 1384 * |
| 黄林等: "一种全解偶的分布式多智能体模型构造方法", 《海军工程大学学报》, vol. 35, no. 03, pages 106 - 112 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116775220B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5377309A (en) | Software work tool | |
| CN101707399B (en) | Method and system for acquiring electric energy information | |
| CN111949454B (en) | Database system based on micro-service component and related method | |
| CN111324445A (en) | Task scheduling simulation system | |
| CN112600891A (en) | Edge cloud cooperation system based on information physical fusion and working method | |
| CN111654416B (en) | Internet of things testing cloud platform and method | |
| CN109840142A (en) | Thread control method, device, electronic equipment and storage medium based on cloud monitoring | |
| CN108416657B (en) | Order generation method and equipment based on consultation service | |
| CN111064672A (en) | Cloud platform communication system, election method and resource scheduling management method | |
| CN109977022A (en) | Inspection method, device, system and the storage medium of game resource | |
| CN110413384A (en) | Delayed tasks processing method and processing device, storage medium, electronic equipment | |
| CN112347636A (en) | Equipment guarantee simulation modeling method based on Multi-Agent technology | |
| CN108848132A (en) | A kind of distribution scheduling station system based on cloud | |
| CN110362315A (en) | Software systems dispatching method and device based on DAG | |
| CN114020413A (en) | Distributed reinforcement learning system design method based on Kubernetes container cluster | |
| CN111324460B (en) | Power monitoring control system and method based on cloud computing platform | |
| CN111447096A (en) | Election method and election system based on cloud platform communication system | |
| CN111447097A (en) | Cloud platform resource scheduling management method and system | |
| CN116775220B (en) | Distributed simulation optimization method, system, equipment and medium based on asynchronous process | |
| CN116737560B (en) | Intelligent training system based on intelligent guide control | |
| CN101390056A (en) | Application system intelligent optimizer | |
| CN112581080A (en) | Lightweight distributed workflow engine construction system | |
| CN106850283B (en) | Event-driven cloud AC alarm processing system and method | |
| CN110276152A (en) | A kind of band non-critical time management method of time remaining of parallel discrete time emulation | |
| CN112769964B (en) | Method for yann support hybrid operation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |