Stack Overflow
Stack Overflow

Questions tagged [multi-agent]

A Multi-Agent System (MAS) is a system composed of multiple interacting intelligent agents within a given environment based on the new paradigm for conceptualizing, designing, and implementing software systems.

A Multi-Agent system (MAS) is a computerized system composed of multiple interacting intelligent agents within an environment based on the new paradigm for conceptualizing, designing, and implementing software systems. Multi-agent systems can be used to solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include some methodical, functional, procedural or algorithmic search, find and processing approach.

155 questions
1
vote
1 answer

Agent's behaviour in Multi-agent systems?

I have request agent and several resource agents in my project. I created a agent application and when I run this application every time I got one result. thats mean I call methods step by step without going accessing these behaviours in random…
Rosh
  • 730
  • 2
  • 12
  • 32
1
vote
1 answer

Synchronise all agent actions with TimeSteppedEnvironment in Jason AgentSpeak

I am currently exploring how Jason deals with a synchronized environment in which one agent must wait till others perform an action. Besides, when all agents have done, env needs to save info to environment models as well. From the document, Jason…
Bryan
  • 1,477
  • 1
  • 21
  • 38
1
vote
0 answers

Ray tune samples more than one value for the same model in multi-agent environment

So I have this weird behavior of ray tune that I can't make sense of. What I'm trying to do: I have setup a custom rllib multi-agent env with two agents Both agents have different observation and action spaces Both should be trained with PPO but…
Pat396
  • 21
  • 3
1
vote
1 answer

Specifying observation space for Q-Mix in ray

I see that I have to define players observations for using Qmix + LSTM as here https://github.com/ray-project/ray/issues/8407#issuecomment-627401186 or as in this…
ckorzhik
  • 758
  • 2
  • 7
  • 21
1
vote
0 answers

How can i get the Mesa agent using their unique_id in Python?

I am using the Python library Mesa for modeling a multiagent system. Is there a way to get the agent itself if you just have its unique_id? I have one agent save the id of another agent, which at a later point in time the agent tries to interact…
JoSch
  • 11
  • 1
1
vote
2 answers

How to prevent my reward sum received during evaluation runs repeating in intervals when using RLlib?

I am using Ray 1.3.0 (for RLlib) with a combination of SUMO version 1.9.2 for the simulation of a multi-agent scenario. I have configured RLlib to use a single PPO network that is commonly updated/used by all N agents. My evaluation settings look…
hridayns
  • 697
  • 8
  • 16
1
vote
0 answers

What is the difference between "Cooperative Pathfinding" and "Multi-Agent Pathfinding"?

So recently I was reading a research paper titled "Cooperative Pathfinding" by David Silver which mentioned that Cooperative Pathfinding is a multi-agent path planning problem ... From my understanding both the terms seem to be the same to me since…
AnonSar
  • 556
  • 1
  • 7
  • 24
1
vote
0 answers

try to revise the inplace operation error:one of the variables needed for gradient computation has been modified by an inplace operation:

I have two agents a and b:they use the same network stucture.and I try to use replaybuffer to update the parameters of networks.If i update a, then update b would bring the error:one of the variables needed for gradient computation has been modified…
Mr_qiaozhi
  • 13
  • 2
1
vote
0 answers

Correct use of a2c.A2cTrainer Rllib with gym and pettingzoo

I'm building a speaker listener training environment with rllib from this article. Using pettingzoo and supersuit. I've encountered the following error: NotImplementedError: Cannot convert a symbolic Tensor (default_policy/cond/strided_slice:0) to a…
user13399343
  • 11
  • 2
1
vote
1 answer

Multi-agent reinforcement learning environment Public transport problem

For my Msc thesis I want to apply multi-agent RL to a bus control problem. The idea is that the busses operate on a given line, but without a timetable. The busses should have bus stops where passengers accumulate over time and pick them up, the…
CEJoe
  • 11
  • 1
1
vote
1 answer

How to write a method that checks if an agent is done with a task in Osbrain?

I have a question on how to write a proper function that checks if an agent is done with their task in Osbrain. I have three agents, the Transport agent, Node agent and the Coordinator agent. The coordinator agent's main task is to synchronize the…
Folorunblues
  • 13
  • 2
1
vote
0 answers

Multiagent in Python using Spade localhost configuration issue

I want to try Multi Agent programming in Python using SPADE, but i can't seem to make this simple example work. The error refers to the server, so how can i set up the agents to work in the localhost ? here is my code : class SenderAgent(Agent): …
Venom
  • 77
  • 8
1
vote
0 answers

Data structure for times that a position has been occupied, with fast way to change these times

So I'm looking for a good data structure to keep track of agents in a multi-agent system. But i can't think of a fast way to implement access to each position and check at what time the agents or objects has been to this position. Furthermore these…
CLover32
  • 33
  • 9
1
vote
1 answer

How to set up rllib multi-agent PPO?

I have a very simple multi-agent environment set up for use with ray.rllib, and I'm trying to run a simple baseline test of a PPO vs. Random Policy training scenario as follows: register_env("my_env", lambda _: MyEnv(num_agents=2)) mock =…
deepmindz
  • 598
  • 1
  • 6
  • 14
1
vote
1 answer

MAS platform written in python

Im looking for a relevant MAS (multi agent system) platform written in python which has the same features and functionality of JADE. Any recommendations?. thx.
user10191177
1 2
3
…
10 11