Multi-agent reward analysis for learning in noisy domains
Explore this paper's citation graph
Summary
This paper presents a new reward evaluation method that provides a visualization of the tradeoff between coordination among the agents and the difficulty of the learning problem each agent faces, and shows that in the more difficult dynamic domain, this method provides a two order of magnitude speedup in selecting a good reward.
- Type
- article
- Published
- 2005-07-25
- Cited by
- 47
- References
- 27
- Access
- Open access
- OpenAlex
- https://openalex.org/W1977031068
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:9734644
Keywords
Computer science, Visualization, A priori and a posteriori, Domain (mathematical analysis), Property (philosophy)
References
- Collectives and Design Complex Systems
- New Directions: Robotics: Coordination and Learning in Multirobot Systems
- Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
- Introduction to Reinforcement Learning
- Neural networks for pattern recognition
- Visualization of radial basis function networks
- Collective intelligence for control of distributed dynamical systems
- Adaptivity in agent-based routing for data networks
- Improving Search Algorithms by Using Intelligent Coordinates
- Visualizing processes in neural networks
- Improving Elevator Performance Using Reinforcement Learning
- Collective Intelligence and Braess' Paradox
- Reinforcement Learning: An Introduction
- Neural Networks: A Comprehensive Foundation
- Learning sequences of actions in collectives of autonomous agents
- Visualization methods for neural networks
- Optimal Payoff Functions for Members of Collectives
- Gradient Descent for General Reinforcement Learning
- The Dynamic Selection of Coordination Mechanisms
- Connectionist Learning Procedures
Cited by
- A decision-theoretic characterization of organizational influences
- Distributed Decision-Making and TaskCoordination in Dynamic, Uncertain andReal-Time Multiagent Environments
- Learning agents for distributed and robust spacecraft power management
- CLEAN Learning to Improve Coordination and Scalability in Multiagent Systems
- Regulating air traffic flow with coupled agents
- Testing a Purportedly More Learnable Auction Mechanism
- Analyzing and visualizing multiagent rewards in dynamic and stochastic domains
- Distributed agent-based air traffic flow management
- Research on Persuasion Type Argument-negotiation System Based on Agent and Its State of Arts
- Evolving distributed resource sharing for cubesat constellations
- Improving quality of data user experience in 4G distributed telecommunication systems
- Handling Communication Restrictions and Team Formation in Congestion Games
- A multiagent approach to managing air traffic flow
- The China Air Traffic Flow Management Problem
- Individual versus Difference Rewards on Reinforcement Learning for Route Choice
- Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems
- Maximizing Secondary-User Satisfaction in Large-Scale DSA Systems Through Distributed Team Cooperation
- Distributed resource and service management for large-scale dynamic spectrum access systems through coordinated learning
- Combining coordination mechanisms to improve performance in multi-robot teams
- Multiagent Metareasoning through Organizational Design
Related papers
- Another view on parallel speedup
- Shared virtual memory and generalized speedup
- Toward a better parallel performance metric
- Speedup for Multi-Level Parallel Computing
- Scalable Problems and Memory-Bounded Speedup
- Performance Considerations of Shared Virtual Memory Machines
- Program Speedup in a Heterogeneous Computing Network
- Estimating the Speedup in Parallel Parsing.
- Optimal-processor-set speedup of SMP cluster
- An effective speedup metric considering I/O constraint in large-scale parallel computer systems