Abstract:
Many problems impede the design of multiagent systems, not the least of which is the passing of information between agents. While others hand implement communication routes and semantics, we explore a method by which communication can evolve. In the experiments described here, we model agents as connectionist networks. We supply each agent with a number of communications channels implemented by the addition of both input and output units for each channel. The output units initiate environmental signals whose amplitude decay over distance and are perturbed by environmental noise. An agent does not receive input from other individuals, rather the agent's input reflects the summation of all other agents' output signals along that channel. Because we use real-valued activations, the agents communicate using real-valued vectors. Under our evolutionary program, GNARL, the agents coevolve a communication scheme over continuous channels which conveys task-specific information. 1. INTRODUCTION...
Citations
|
160
|
An Evolutionary Algorithm that Constructs Recurrent Neural Networks
– Angeline, Saunders, et al.
- 1993
|
|
109
|
Evolution of communication in artificial organisms
– Werner, Dyer
- 1991
|
|
57
|
Artificial Intelligence Meets Natural Stupidity
– McDermott
- 1981
|
|
50
|
Challenges for Complete Creature Architectures
– Brooks
- 1990
|
|
48
|
Antfarm: Towards simulated evolution
– Collins, Jefferson
- 1991
|
|
48
|
Evolving Artificial Intelligence
– Fogel
- 1992
|
|
43
|
Altruism in the evolution of communication
– Ackley, Littman
- 1994
|
|
41
|
Dimensions of Communication and Social Organization in Multi-Agent Robotic Systems", From animals to animats 2
– Arkin, Hobbs
- 1992
|
|
28
|
Evolution of herding behavior in artificial animals
– Werner, Dyer
|
|
22
|
Fool’s gold: Extracting finite state machines from recurrent network dynamics
– Kolen
- 1994
|
|
20
|
Recurrent Networks: State Machines or Iterated Function Systems
– Kolen
- 1994
|
|
15
|
The observer's paradox: Apparent computational complexity in physical systems
– Kolen, Pollack
- 1994
|
|
7
|
Structural and behavioral evolution of recurrent networks
– Saunders, Angeline, et al.
- 1994
|
|
4
|
Synthetic ecology: An approach to the study of communication
– MacLennan
- 1991
|
|
3
|
Evolution as a theme in artificial life: The genesys / tracker system
– Jefferson, Collins, et al.
- 1992
|
|
1
|
The importance of leaky levels for behavior-based AI. From Animals to Animats 3
– Saunders, Kolen, et al.
- 1994
|