Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs

@inproceedings{Blynel2003ExploringTT,
  title={Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs},
  author={Jesper Blynel and D. Floreano},
  booktitle={EvoWorkshops},
  year={2003}
}
  • Jesper Blynel, D. Floreano
  • Published in EvoWorkshops 2003
  • Computer Science
  • This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double T-Maze navigation tasks, where the robot has to locate and "remember" the position of a reward-zone. The "learning" comes about without modifications of synapse strengths, but simply from internal network dynamics, as proposed by [12]. Neural controllers are evolved in simulation and in the simple case evaluated on a real robot… CONTINUE READING
    82 Citations
    Evolving Neural Turing Machines for Reward-based Learning
    • 22
    • PDF
    Hierarchical evolution of robotic controllers for complex tasks
    • 22
    • Highly Influenced
    • PDF
    Structured Composition of Evolved of Robotic Controllers.
    • 1
    • Highly Influenced
    • PDF
    Solving Mazes using an Artificial Developmental Neuron
    • 5
    • PDF
    A maze learning comparison of Elman, long short-term memory, and Mona neural networks
    • 13
    • PDF
    With a little help from selection pressures: evolution of memory in robot controllers
    • 23
    • PDF
    Autonomous Specialization in a Multi-Robot System using Evolving Neural Networks
    • 3
    • PDF
    A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors
    • 4
    The Dynamics of Associative Learning in Evolved Model Circuits
    • 28
    • PDF

    References

    SHOWING 1-10 OF 15 REFERENCES
    Evolving Reinforcement Learning-Like Abilities for Robots
    • 18
    • PDF
    Model-based learning for mobile robot navigation from the dynamical systems perspective
    • J. Tani
    • Computer Science, Medicine
    • IEEE Trans. Syst. Man Cybern. Part B
    • 1996
    • 350
    • PDF
    Sequential Behavior and Learning in Evolved Dynamical Neural Networks
    • 165
    • PDF
    Evolving Mobile Robots in Simulated and Real Environments
    • 133
    • PDF
    Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis
    • 311
    • PDF