No abstract available.
A logical approach to high-level agent control
Recent work in animated human-like agent has made impressive progress toward generating agents with believable appearances and realistic motions for the interactive applications of inhabited virtual worlds. It remains difficult, however, to instruct ...
The BOID architecture: conflicts between beliefs, obligations, intentions and desires
In this paper we introduce the so-called Beliefs-Obligations-Intentions-Desires or BOID architecture. It contains feedback loops to consider all effects of actions before committing to them, and mechanisms to resolve conflicts between the outputs of its ...
Evolving real-time agent control for large-scale MAS
Control for agents situated in multi- agent systems is a complex problem. This is particularly true in hard, open, dynamic environments where resource, privacy, bandwidth, and computational limitations impose restrictions on the type of information that ...
Learning structured reactive navigation plans from executing MDP navigation policies
Autonomous robots, such as robot office couriers, need navigation routines that support flexible task execution and effective action planning. This paper describes \xfl, a system that learns structured symbolic navigation plans. Given a navigation task, ...
Using rat navigation models to learn orientation from visual input on a mobile robot
Rodents possess extraordinary navigation abilities that are far in excess of what current state- of- the- art robot agents are capable of. This paper describes research that is part of larger project aimed at developing a robot navigation system that is ...
Architecture and preliminary experimental results for emotionally grounded symbol acquisition
In this paper, we propose a novel concept, “Emotionally Grounded Symbol Acquisition”, which is an extended idea of well- studied concept, “Physically Grounded Symbol Acquisition”. We think it is important for an autonomous robot to ground symbols not ...
Collaborative multiagent learning for classification tasks
Multiagent learning differs from standard machine learning in that most existing learning methods assume that all knowledge is available locally in a single agent. In multiagent systems, this assumption does not hold because relevant knowledge is ...
A multi-agent reinforcement learning method for a partially-observable competitive game
This article proposes a reinforcement learning (RL) method based on an actor-critic architecture, which can be applied to partially-observable multi-agent competitive games. As an example, we deal with a card game “Hearts”. In our method, the actor ...
An auction-based method for decentralized train scheduling
We present a computational study of an auction-based method for decentralized train scheduling. The method is well suited to the natural information and control structure of mod- ern railroads. We assume separate network territories, with an autonomous ...
Automated negotiation from declarative contract descriptions
Our approach for automating the negotiation of business contracts proceeds in three broad steps. First, determine the structure of the negotiation process byapplying general knowledge about auctions and domain-specific knowledge about the contract ...
An agent bidding strategy based on fuzzy logic in a continuous double auction
This paper presents the design and implementation of a fuzzy logic based bidding strategy, the FL-strategy, for an agent in a Continuous Double Auction (CDA). Experiment results show that the FL-strategy outperforms some of the commonly used bidding ...
MORPHEUS: a more scalable comparison-shopping agent
This paper proposes a more scalable comparison-shopping agent named MORPHEUS. MORPHEUS presents simple but robust inductive learning algorithm that automatically constructs wappers.
Matchmaking for autonomous agents in electronic marketplaces
Matchmaking is the process of mediating demand and supply based on profile information. Matchmaking plays a crucial role in agent-based electronic marketplaces: the problem to be solved is to find the most appropriate agents, products, or services for a ...
Simultaneous optimization of multiple criteria for efficient agent service brokering
Efficient, flexible and dynamic allocation of combination of services to satisfy advanced service requirements in multi- agent systems is a crucial problem. Optimal service allocation based on a single criterion is NP- Complete. However, service ...
Vicious strategies for Vickrey auctions
We show that the Vickrey auction, despite its theoretical benefits, is inappropriate if “antisocial” agents participate in the auction process. More specifically, an antisocial attitude for economic agents that makes {\em reducing the profit of ...
Design of a trust model for a secure multi-agent marketplace
A general trust model and security framework for a multi- agent system designed to manage resources in future mobile communications networks is described. The multi- agent system is being developed as part of the IST SHUFFLE project [1]. A business ...
Exploring decision processes in multi-agent automated contracting
We are interested in multi-agent contracting, in which customers must solicit the resources and capabilities of other, self-interested agents in order to accomplish their goals. Goals may involve the execution of multi-step plans, in which different ...
Determining bidding strategies in sequential auctions: quasi-linear utility and budget constraints
In this paper, we develop a new method for finding an optimal bidding strategy in sequential auctions, using a dynamic programming technique. The existing method assumes the utility of a user is represented in an additive form. Thus, the remaining ...
Cited By
-
Neufeld E, Bartocci E, Ciabattoni A and Governatori G (2022). Enforcing ethical goals over reinforcement-learning policies, Ethics and Information Technology, 10.1007/s10676-022-09665-8, 24:4, Online publication date: 1-Dec-2022.
-
Ilarri S, Mena E and Illarramendi A Self-Synchronization of Cooperative Agents in a Distributed Environment Multi-Agent Systems and Applications III, 10.1007/3-540-45023-8_7, (51-60)
Index Terms
- Proceedings of the fifth international conference on Autonomous agents
Recommendations
Acceptance Rates
Year | Submitted | Accepted | Rate |
---|---|---|---|
AGENTS '01 | 248 | 66 | 27% |
AGENTS '98 | 180 | 57 | 32% |
AGENTS '97 | 171 | 59 | 35% |
Overall | 599 | 182 | 30% |