![Page 1: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/1.jpg)
Multi-Agent Systems:Overview and Research Directions
CMSC 471
December 1 and 3, 2009
Prof. Marie desJardins
![Page 2: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/2.jpg)
Outline
What’s an Agent? Multi-Agent Systems
Cooperative multi-agent systems Competitive multi-agent systems
MAS Research Directions Organizational structures Communication limitations Learning in multi-agent systems
![Page 3: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/3.jpg)
What’s an Agent?
![Page 4: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/4.jpg)
What’s an agent?
Weiss, p. 29 [after Wooldridge and Jennings]: “An agent is a computer system that is situated in some
environment, and that is capable of autonomous action in this environment in order to meet its design objectives.”
Russell and Norvig, p. 7: “An agent is just something that perceives and acts.”
Rosenschein and Zlotkin, p. 4: “The more complex the considerations that [a] machine takes into
account, the more justified we are in considering our computer an ‘agent,’ who acts as our surrogate in an automated encounter.”
![Page 5: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/5.jpg)
What’s an agent? II
Ferber, p. 9: “An agent is a physical or virtual entity
a) Which is capable of acting in an environment,b) Which can communicate directly with other agents,c) Which is driven by a set of tendencies…,d) Which possesses resources of its own,e) Which is capable of perceiving its environment…,f) Which has only a partial representation of this environment…,g) Which possesses skills and can offer services,h) Which may be able to reproduce itself,i) Whose behavior tends towards satisfying its objectives,
taking account of the resources and skills available to it and depending on its perception, its representations and the communications it receives.”
![Page 6: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/6.jpg)
OK, so what’s an environment?
Isn’t any system that has inputs and outputs situated in an environment of sorts?
![Page 7: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/7.jpg)
What’s autonomy, anyway?
Jennings and Wooldridge, p. 4: “[In contrast with objects, we] think of agents as
encapsulating behavior, in addition to state. An object does not encapsulate behavior: it has no control over the execution of methods – if an object x invokes a method m on an object y, then y has no control over whether m is executed or not – it just is. In this sense, object y is not autonomous, as it has no control over its own actions…. Because of this distinction, we do not think of agents as invoking methods (actions) on agents – rather, we tend to think of them requesting actions to be performed. The decision about whether to act upon the request lies with the recipient.”
Is an if-then-else statement sufficient to create autonomy?
![Page 8: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/8.jpg)
So now what?
If those definitions aren’t useful, is there a useful definition? Should we bother trying to create “agents” at all?
![Page 9: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/9.jpg)
Multi-Agent Systems
![Page 10: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/10.jpg)
Multi-agent systems
Jennings et al.’s key properties: Situated Autonomous Flexible:
Responsive to dynamic environmentPro-active / goal-directedSocial interactions with other agents and humans
Research questions: How do we design agents to interact effectively to solve a wide range of problems in many different environments?
![Page 11: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/11.jpg)
Aspects of multi-agent systems
Cooperative vs. competitive Homogeneous vs. heterogeneous Macro vs. micro
Interaction protocols and languages Organizational structure Mechanism design / market economics Learning
![Page 12: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/12.jpg)
Topics in multi-agent systems
Cooperative MAS: Distributed problem solving: Less autonomy Distributed planning: Models for cooperation and teamwork
Competitive or self-interested MAS: Distributed rationality: Voting, auctions Negotiation: Contract nets
![Page 13: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/13.jpg)
Typical (cooperative) MAS domains
Distributed sensor network establishment Distributed vehicle monitoring Distributed delivery
![Page 14: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/14.jpg)
Distributed sensing
Track vehicle movements using multiple sensors Distributed sensor network establishment:
Locate sensors to provide the best coverage Centralized vs. distributed solutions
Distributed vehicle monitoring: Control sensors and integrate results to track vehicles as they move
from one sensor’s “region” to another’s Centralized vs. distributed solutions
![Page 15: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/15.jpg)
Distributed delivery
Logistics problem: move goods from original locations to destination locations using multiple delivery resources (agents)
Dynamic, partially accessible, nondeterministic environment (goals, situation, agent status)
Centralized vs. distributed solution
![Page 16: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/16.jpg)
Cooperative Multi-Agent Systems
![Page 17: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/17.jpg)
Distributed problem solving/planning
Cooperative agents, working together to solve complex problems with local information
Partial Global Planning (PGP): A planning-centric distributed architecture
SharedPlans: A formal model for joint activity Joint Intentions: Another formal model for joint activity STEAM: Distributed teamwork; influenced by joint
intentions and SharedPlans
![Page 18: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/18.jpg)
Distributed problem solving
Problem solving in the classical AI sense, distributed among multiple agents That is, formulating a solution/answer to some complex question Agents may be heterogeneous or homogeneous DPS implies that agents must be cooperative (or, if self-interested,
then rewarded for working together)
![Page 19: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/19.jpg)
Requirements for cooperative activity
(Grosz) -- “Bratman (1992) describes three properties that must be met to have ‘shared cooperative activity’: Mutual responsiveness Commitment to the joint activity Commitment to mutual support”
![Page 20: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/20.jpg)
Joint intentions
Theoretical framework for joint commitments and communication
Intention: Commitment to perform an action while in a specified mental state
Joint intention: Shared commitment to perform an action while in a specified group mental state
Communication: Required/entailed to establish and maintain mutual beliefs and join intentions
![Page 21: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/21.jpg)
SharedPlans
SharedPlan for group action specifies beliefs about how to do an action and subactions
Formal model captures intentions and commitments towards the performance of individual and group actions
Components of a collaborative plan (p. 5): Mutual belief of a (partial) recipe Individual intentions-to perform the actions Individual intentions-that collaborators succeed in their subactions Individual or collaborative plans for subactions
Very similar to joint intentions
![Page 22: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/22.jpg)
STEAM: Now we’re getting somewhere!
Implementation of joint intentions theory Built in Soar framework Applied to three “real” domains Many parallels with SharedPlans
General approach: Build up a partial hierarchy of joint intentions Monitor team and individual performance Communicate when need is implied by changing mental state &
joint intentions
Key extension: Decision-theoretic model of communication selection
![Page 23: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/23.jpg)
Competitive Multi-Agent Systems
![Page 24: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/24.jpg)
Distributed rationality
Techniques to encourage/coax/force self-interested agents to play fairly in the sandbox
Voting: Everybody’s opinion counts (but how much?) Auctions: Everybody gets a chance to earn value (but how
to do it fairly?) Contract nets: Work goes to the highest bidder Issues:
Global utility Fairness Stability Cheating and lying
![Page 25: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/25.jpg)
Pareto optimality
S is a Pareto-optimal solution iff S’ (x Ux(S’) > Ux(S) → y Uy(S’) < Uy(S)) i.e., if X is better off in S’, then some Y must be worse off
Social welfare, or global utility, is the sum of all agents’ utility If S maximizes social welfare, it is also Pareto-optimal (but not
vice versa)
X’s utility
Y’s utility
Which solutionsare Pareto-optimal?
Which solutionsmaximize global utility(social welfare)?
![Page 26: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/26.jpg)
Stability
If an agent can always maximize its utility with a particular strategy (regardless of other agents’ behavior) then that strategy is dominant
A set of agent strategies is in Nash equilibrium if each agent’s strategy Si is locally optimal, given the other agents’ strategies No agent has an incentive to change strategies Hence this set of strategies is locally stable
![Page 27: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/27.jpg)
Prisoner’s Dilemma
Cooperate Defect
Cooperate 3, 3 0, 5
Defect 5, 0 1, 1
AB
![Page 28: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/28.jpg)
Prisoner’s Dilemma: Analysis
Pareto-optimal and social welfare maximizing solution: Both agents cooperate
Dominant strategy and Nash equilibrium: Both agents defect
Cooperate Defect
Cooperate 3, 3 0, 5
Defect 5, 0 1, 1
Why?
AB
![Page 29: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/29.jpg)
Voting
How should we rank the possible outcomes, given individual agents’ preferences (votes)?
Six desirable properties (which can’t all simultaneously be satisfied): Every combination of votes should lead to a ranking Every pair of outcomes should have a relative ranking The ranking should be asymmetric and transitive The ranking should be Pareto-optimal Irrelevant alternatives shouldn’t influence the outcome Share the wealth: No agent should always get their way
![Page 30: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/30.jpg)
Voting protocols
Plurality voting: the outcome with the highest number of votes wins Irrelevant alternatives can change the outcome: The Ross Perot
factor Borda voting: Agents’ rankings are used as weights, which
are summed across all agents Agents can “spend” high rankings on losing choices, making their
remaining votes less influential Binary voting: Agents rank sequential pairs of choices
(“elimination voting”) Irrelevant alternatives can still change the outcome Very order-dependent
![Page 31: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/31.jpg)
Auctions
Many different types and protocols All of the common protocols yield Pareto-optimal outcomes But… Bidders can agree to artificially lower prices in order
to cheat the auctioneer What about when the colluders cheat each other?
(Now that’s really not playing nicely in the sandbox!)
![Page 32: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/32.jpg)
Contract nets
Simple form of negotiation Announce tasks, receive bids, award contracts Many variations: directed contracts, timeouts, bundling of
contracts, sharing of contracts, … There are also more sophisticated dialogue-based
negotiation models
![Page 33: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/33.jpg)
MAS Research Directions
![Page 34: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/34.jpg)
Agent organizations
“Large-scale problem solving technologies” Multiple (human and/or artificial) agents Goal-directed (goals may be dynamic and/or conflicting) Affects and is affected by the environment Has knowledge, culture, memories, history, and capabilities
(distinct from individual agents) Legal standing is distinct from single agent Q: How are MAS organizations different from human
organizations?
![Page 35: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/35.jpg)
Organizational structures
Exploit structure of task decomposition Establish “channels of communication” among agents
working on related subtasks Organizational structure:
Defines (or describes) roles, responsibilities, and preferences
Use to identify control and communication patterns:Who does what for whom: Where to send which
task announcements/allocationsWho needs to know what: Where to send which
partial or complete results
![Page 36: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/36.jpg)
Communication models
Theoretical models: Speech act theory Practical models:
Shared languages like KIF, KQML, DAML Service models like DAML-S Social convention protocols
![Page 37: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/37.jpg)
Communication strategies
Send only relevant results at the right time Conserve bandwidth, network congestion, computational
overhead of processing data Push vs. pull Reliability of communication (arrival and latency of
messages) Use organizational structures, task decomposition,
and/or analysis of each agent’s task to determine relevance
![Page 38: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/38.jpg)
Communication structures
Connectivity (network topology) strongly influences the effectiveness of an organization
Changes in connectivity over time can impact team performance: Move out of communication range coordination
failures Changes in network structure reduced (or increased)
bandwidth, increased (or reduced) latency
![Page 39: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/39.jpg)
Learning in MAS
Emerging field to investigate how teams of agents can learn individually
and as groups Distributed reinforcement learning: Behave as an
individual, receive team feedback, and learn to individually contribute to team performance
Distributed reinforcement learning: Iteratively allocate “credit” for group performance to individual decisions
Genetic algorithms: Evolve a society of agents (survival of the fittest)
Strategy learning: In market environments, learn other agents’ strategies
![Page 40: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/40.jpg)
Adaptive organizational dynamics
Potential for change: Change parameters of organization over time That is, change the structures, add/delete/move agents,
… Adaptation techniques:
Genetic algorithms Neural networks Heuristic search / simulated annealing Design of new processes and procedures Adaptation of individual agents
![Page 41: Multi-Agent Systems: Overview and Research Directions](https://reader030.vdocuments.site/reader030/viewer/2022032806/56813472550346895d9b55df/html5/thumbnails/41.jpg)
Conclusions and directions
“Agent” means many different things Different types of “multi-agent systems”:
Cooperative vs. competitive Heterogeneous vs. homogeneous Micro vs. macro
Lots of interesting/open research directions: Effective cooperation strategies “Fair” coordination strategies and protocols Learning in MAS Resource-limited MAS (communication, …)