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} }
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
Figures and Topics from this paper
82 Citations
Hierarchical evolution of robotic controllers for complex tasks
- Computer Science
- 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)
- 2012
- 22
- Highly Influenced
- PDF
Exploring multi-objective evolution of robot brains in obstacle and maze environments with varying complexities
- Engineering
- 2008
A maze learning comparison of Elman, long short-term memory, and Mona neural networks
- Computer Science, Medicine
- Neural Networks
- 2010
- 13
- PDF
With a little help from selection pressures: evolution of memory in robot controllers
- Computer Science
- ALIFE
- 2012
- 23
- PDF
Autonomous Specialization in a Multi-Robot System using Evolving Neural Networks
- Computer Science
- 2011
- 3
- PDF
A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors
- Computer Science
- ICANNGA
- 2011
- 4
The Dynamics of Associative Learning in Evolved Model Circuits
- Computer Science
- Adapt. Behav.
- 2007
- 28
- PDF
References
SHOWING 1-10 OF 15 REFERENCES
Integrating reactive, sequential, and learning behavior using dynamical neural networks
- Computer Science
- 1994
- 105
Levels of dynamics and adaptive behavior in evolutionary neural controllers
- Computer Science
- 2002
- 62
- PDF
Evolving integrated controllers for autonomous learning robots using dynamic neural networks
- Computer Science
- 2002
- 24
Model-based learning for mobile robot navigation from the dynamical systems perspective
- Computer Science, Medicine
- IEEE Trans. Syst. Man Cybern. Part B
- 1996
- 350
- PDF
Sequential Behavior and Learning in Evolved Dynamical Neural Networks
- Computer Science
- Adapt. Behav.
- 1994
- 165
- PDF
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems
- Computer Science, Medicine
- Neural Networks
- 1999
- 290
- PDF
Evolving Mobile Robots in Simulated and Real Environments
- Computer Science, Medicine
- Artificial Life
- 1995
- 133
- PDF
Neuromodulation of Reactive Sensorimotor Mappings as a Short-Term Memory Mechanism in Delayed Response Tasks
- Psychology, Computer Science
- Adapt. Behav.
- 2002
- 70
Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis
- Computer Science
- Adapt. Behav.
- 1997
- 311
- PDF