Questions tagged [multi-agent-systems]

For questions related to multi-agent systems (MAS), which are systems that involve multiple agents (each of them can have different skills) that cooperate with each other and interact with the environment. There are several challenges faced by MAS, including coordination between agents, security, and task allocation. Multi-agent systems have been applied in areas such as computer science, civil engineering, and electrical engineering.

Filter by
Sorted by
Tagged with
0 votes
0 answers
20 views

Are there assumptions made about Self-Play that don't hold up in regular MA competition?

I read about this paper Efficient Competitive Self-Play Policy Optimization which proposes an algorithm for training a population of agents with self-play using a perturbation based matchmaking ...
user avatar
  • 85
0 votes
0 answers
24 views

Multi-task learning with heterogenous features

I recently discovered multi-task learning using neural networks (an excellent introduction here), and find it a fascinating research area. Common approaches seem to be: Learning a shared ...
user avatar
  • 1
1 vote
0 answers
28 views

Book/course recommendation on game theory application to multi-agent system (reinforcement learning)

Is there any great game theory book or course that discusses the application of game theory to modern reinforcement learning or multi-agent systems? Or a classic reference book that can help me get a ...
user avatar
  • 431
0 votes
1 answer
78 views

Can a Reinforcement Learning problem with multiple simultaneous actions be formalized as a Multiagent Partially Observable Markov Decision Process?

Consider the following decision making problem. We have a controller that selects locations from a grid of coordinates and captures an image (observation $o_t$) with a camera at each location (action $...
user avatar
0 votes
0 answers
23 views

multi agent deep deterministic policy gradient for discrete actions

I am solving a multi agent problem where each agent has a critic and actor. The problem I am solving has discrete actions and discrete states. I came cross multi-agent deep deterministic policy ...
user avatar
0 votes
0 answers
21 views

Why does fictitious self-play use the data collected by the average strategy for reinforcement learning?

I'm reading paper "Fictitious Self-Play in Extensive-Form Games", which introduces fictitious self-play(FPS). In extensive-form games, let $\beta$ be the best response strategy, $\pi$ be the ...
user avatar
  • 431
1 vote
0 answers
71 views

How to parallelize multi-agent DDPG (MADDPG)

I am experimenting with MADDPG algorithm implemented in this repo. Since there were only a few agents (2-3) in the implementation (also in the original paper) steps like parameter updates, action ...
user avatar
  • 167
0 votes
1 answer
71 views

How to implement a rule-based decision maker for an agent-based model?

I had no idea that there is a stack exchange community for A.I. :-/ So I repost this question here in hope of some guidelines. I tried to delve into the materials discussed in AI: A Modern Approach ...
user avatar
1 vote
0 answers
178 views

RLLib - What exactly do the avail_action and action_embed_size represent? How do they work with the action_mask to phase out invalid actions?

So, I'm fairly new to reinforcement learning and I needed some help/explanations as to what the action_mask and avail_action fields alongside the action_embed_size actually mean in RLlib (the ...
user avatar
0 votes
0 answers
21 views

Multi-agent policy gradient, 1 total reward instead of reward in each step, 2 changing action space

I am new in reinforcement learning and not sure I have the right understanding of multi-agent policy gradient. 1, in my question, each agent has its own action space. When doing the sampling, for each ...
user avatar
0 votes
0 answers
249 views

RLlib's Multi-agent PPO continuous actions turn into nan

After some amount of training on a custom Multi-agent sparse-reward environment using RLlib's (1.4.0) PPO network, I found that my continuous actions turn into nan (explodes?) which is probably caused ...
user avatar
  • 223
-2 votes
1 answer
192 views

Policy Gradient ( Advantage actor-critic) for multiple simultaneous continuous actions

i'm trying to solve a problem in which i need to carry out reinforcement learning with multiple simultaneous actions in continuous action space . i checked the multiagent structure; however, im trying ...
user avatar
1 vote
0 answers
37 views

Why is the number of examined nodes $ O(b^{3d/4})$ in $\alpha$-$\beta$ pruning?

I'm taking a course 'Introduction to AI' and, in one of the tutorials, it was written that when pruning the game tree using $\alpha$-$\beta$ boundaries, the number of nodes that will be developed, ...
user avatar
3 votes
2 answers
320 views

Why does Alpha Zero's Neural Network flip the board to be oriented towards the current player?

While reading the AlphaZero paper in preparation to code my own RL algorithm to play Chess decently well, I saw that the "The board is oriented to the perspective of the current player." I ...
user avatar
3 votes
1 answer
467 views

How does the Alpha Zero's move encoding work?

I am a beginner in AI. I'm trying to train a multi-agent RL algorithm to play chess. One issue that I ran into was representing the action space (legal moves/or honestly just moves in general) ...
user avatar
1 vote
0 answers
19 views

How would I design a finite budget, cascaded multi agent deep reinforcement learning model?

In most of the multi-agent reinforcement learning models I've found, it seems to generate the observations for each of the agents simultaneously and then uses a centralized critic to assess all of the ...
user avatar
  • 111
2 votes
0 answers
61 views

What place do Agent Communications Language have in Multi-Agent Systems nowadays?

I am currently working on implementing a Multi-Agent System for Smart Grids. There's a lot of literature for that and some things confuse me. I have read that there is FIPA, which aimed to create a ...
user avatar
2 votes
1 answer
48 views

Is there multi-agent reinforcement learning model in which (some of the) reward is given by other agent and not by the external environment?

The traditional setting of multiagent reinforcement learning (MARL) is the mode in which there is set of agents and external environment. And the reward is given to each agent - individually or ...
user avatar
  • 773
1 vote
0 answers
297 views

Designing Policy-Network for Deep-RL with Large, Variable Action Space

I am attempting a project involving training an agent to play a game using deep reinforcement learning. This project has a few features that complicate the design of the neural network: The action ...
user avatar
0 votes
1 answer
77 views

How to train the NN of simple agents given a reward system?

I'm not an expert in AI or NN, I gathered most of the information I have from the internet, and I'm looking for advice and guidance. I'm trying to design a NN that is going to be used by all the ...
user avatar
  • 109
0 votes
1 answer
354 views

How to handle a changing in the Reinforcement Learning environment where there is increasing or decreasing in number of agents?

I'm working in A2C and I have an environment where there is increasing or decreasing in the number of agents. The action space in the environment will not change but the state will change when new ...
user avatar
3 votes
1 answer
171 views

Can AlphaZero considered as Multi-Agent Deep Reinforcement Learning?

Can AlphaZero considered as Multi-Agent Deep Reinforcement Learning? I could not find a clear answer on this. I would say yes it is Multi Agent Learning, as there are two Agents playing against each ...
user avatar
  • 33
1 vote
1 answer
83 views

What is the relation between multi-agent learning and reinforcement learning?

What is the relation between multi-agent learning and reinforcement learning? Is one a sub-field of the other? For instance, would it make sense to state that your research interest are multi-agent ...
user avatar
  • 175
2 votes
0 answers
55 views

How does heuristic work with multiple agents?

I have a question for heuristic search with multiple agents. I know how heuristic search works with one agent (ex. one Pacman) but I don't really understand it with multiple agents. Let's say we have ...
user avatar
  • 121
1 vote
1 answer
142 views

Shouldn't the utility function of two-player zero-sum games be in the range $[-1, 1]$?

In Appendix B of MuZero, they say In two-player zero-sum games the value functions are assumed to be bounded within the $[0, 1]$ interval. I'm confused about the boundary: Shouldn't the value/...
user avatar
  • 431
1 vote
0 answers
24 views

Are there any board game appropriate to examine the performance of multiple agents that cooperate both inter-group and intra-group?

I want to find out scenarios that useful to examine the performance of intra-group and inter-group cooperation in MARL. Specifically, I prefer a board game (like sudoku) that is suitable for the ...
user avatar
  • 41
1 vote
0 answers
28 views

Do I need to maintain a separate population in each distributed environment when implementing PBT in a MARL context?

I have questions regarding on how to implement PBT as described in Algorithm 1 (on page 5) in the paper, Population Based Training of Neural Networks to train agents in a MARL (multi-agent ...
user avatar
  • 151
2 votes
1 answer
74 views

Agents meeting in a directed connected graph

We have a directed connected graph, where nodes are places one can go to and edges are the "roads" between places. We have K agents whose goal is to meet in one node. Agents start in ...
user avatar
  • 161
1 vote
2 answers
289 views

Formal proof that every purely reactive agent has behaviorally equivalent standard agent

It kind of makes sense intuitively but I'm not sure about a formal proof. I'll start with briefly listing definitions from Intro to Multiagent systems, Wooldridge, 2002 and then give you my reasoning ...
user avatar
2 votes
0 answers
64 views

What are the examples of agents that is represent these characteristics?

I'm looking for examples of AI systems or agents that best represent these five characteristics (one example for each characteristics): Reactivity Proactivity Adaptability Sociability Autonomy It ...
user avatar
7 votes
1 answer
295 views

How would one implement a multi-agent environment with asynchronous action and rewards per agent?

In a single agent environment, the agent takes an action, then observes the next state and reward: ...
user avatar
  • 173
1 vote
1 answer
225 views

What is the difference between multi-agent and multi-modal systems?

The Wikipedia definitions are as follows Multi-agent systems - A multi-agent system is a computerized system composed of multiple interacting intelligent agents. Multi-modal interaction - Multimodal ...
user avatar
  • 1,359
4 votes
1 answer
111 views

How to represent players in a multi agent environment so each model can distinguish its own player

So I have 2 models trained with the DQN algorithm that I want to train in a multi-agent environment to see how they react with each other. The models were trained in an environment consisting of 0's ...
user avatar
  • 41
2 votes
0 answers
94 views

How does Friend-or-Foe Q-learning intuitively work?

I read about Q-Learning and was reading about multi-agent environments. I tried to read the paper Friend-or-Foe Q-learning, but could not understand anything, except for a very vague idea. What does ...
user avatar
4 votes
0 answers
181 views

Multi Agent Sokoban Search Solvers state of the art

I also asked this question here but I'm repeating it on this SE because I feel it is more relevant. No intention to spam. I am researching into coding a solver for a variant of the Sokoban game with ...
user avatar
1 vote
0 answers
70 views

What is the best method to deal with heterogeneous multi agent system MAS?

Heterogeneity: Based on the heterogeneity of agents MAS can be divided into two categories namely: homogeneous and heterogeneous. Homogeneous MAS include agents that all have the same characteristics ...
user avatar
3 votes
1 answer
2k views

How to deal with the terminal state in SARSA in a multi-agent setting?

I'm training a SARSA agent to update a Q function, but I'm confused about how you handle the final state. In this case, when the game ends and there is no $S'$. For example, the agent performed an ...
user avatar
  • 393
2 votes
1 answer
149 views

Convergence in multi-agent environment

I have a multi-agent environment where agents are trying to optimise the overall energy consumption of their group. Agents can exchange energy between themselves (actions for exchange of energy ...
user avatar
2 votes
0 answers
72 views

Algorithms for multiple agents problems

Can anyone recommend a reinforcement learning algorithm for a multi-agent environment? In my simplified example, I'm implementing a Q-Learning system with different 10 agents. The agents compete for ...
user avatar
1 vote
1 answer
109 views

Can Q-learning working in a multi agent environment where every agent learns a behaviour independently?

I am currently exploring multi-agent reinforcement learning. I have multiple agents that communicate with each other and a central service that maintains the environment state. The central service ...
user avatar
2 votes
1 answer
251 views

Agent collision avoidance java

I am working with a project which is a agent based pedestrian simulation in Java and its is animated with the help of JavaFX. I've tried to read all the social force model papers but my understanding ...
user avatar
  • 21
2 votes
1 answer
57 views

How to choose evaluation functions for features, when network effects are in place (multi-agent systems)?

So, I have this huge amount of data, which has 7 vector features (float from 0 to 1). I am trying to build a kind of recommendation system, with a twist (it uses agents and negotiations and narratives;...
user avatar
  • 278
1 vote
3 answers
138 views

To what extent can artificially intelligent agents reliably predict trends in financial markets?

I've gotten curious about this topic and am wondering what the stack exchange community has to say about it. Also, does anyone know of any professors/researchers who have published papers pertaining ...
user avatar
4 votes
1 answer
142 views

How can I design a hierarchy of agents each of which with different goals?

I read some light material earlier about the possibility of building a hierarchy of agents, where the agents at the leaves solve primitive tasks while higher-level agents are optimized for ...
user avatar
  • 251
3 votes
1 answer
825 views

Goal oriented Action Planning with multiple Agents

I'm a little bit stuck: I implemented an AI with GOAP (Goal oriented Action Planning, http://alumni.media.mit.edu/~jorkin/gdc2006_orkin_jeff_fear.pdf) for a simulation game. That works fine. Now I ...
user avatar
  • 116
7 votes
1 answer
30k views

What are some examples of intelligent agents for each intelligent agent class?

There are several classes of intelligent agents, such as: simple reflex agents model-based reflex agents goal-based agents utility-based agents learning agents Each of these agents behaves slightly ...
user avatar
6 votes
2 answers
173 views

Would a general-purpose AI need to collaborate?

Human beings are more productive in groups than individually, possibly due to the fact that there is a limit to how much one human brain can improve itself in terms of speed of computation and areas ...
user avatar
5 votes
1 answer
119 views

How can thousand-robot swarm coordinate their moves without bumping into each other?

How can a swarm of small robots (like Kilobots) walking close to each other achieve collaboration without bumping into each other? For example, one study shows programmable self-assembly in a thousand-...
user avatar
  • 10k
13 votes
6 answers
426 views

Are there any decentralized examples of AI systems with blockchain technology?

Has there been any attempts to deploy AI with blockchain technology? Are there any decentralized examples of AI networks with no central point of control with AI nodes acting independently (but ...
user avatar