A Reinforcement Learning Exploration Strategy based on Ant

@inproceedings{ForagingMechanismsLaurens1995ARL,
  title={A Reinforcement Learning Exploration Strategy based on Ant},
  author={ForagingMechanismsLaurens and R. and Leerinka and R. Simon and Schultzb and Ahmed I Marwan and Jabriba},
  year={1995}
}
  • ForagingMechanismsLaurens, R., +4 authors Jabriba
  • Published 1995
This paper applies recent results from theoretical biology on the topic of ant trail formation and foraging methods to the problem of exploration in a discrete environment with delayed reinforcement. Three mechanisms that have been identiied in ant trail formation were implemented as an exploration strategy in the adaptive heuristic critic framework, and applied to a well researched robot navigation task. Simulations indicate that in terms of eeciency the mechanisms used by a single ant Lasius… CONTINUE READING