Who started the method


Reinforcement learning theory (Sutton and Barto, 1998)

Sutton RS, Precup D, Singh S. 1999. Between MDPs and semi-
MDPs: A framework for temporal abstraction in reinforcement
learning. Artif Intell 112:181.211.



Broekens J. and DeGroot D. (2004). 
Emergent representations and reasoning in adaptive agents. 
In Proc. 3rd International Conference on Machine Learning and
Applications (pp. 207-214).




==================================================================================================
For Further Challange



<T-maze by RL>


"A Neural Reinforcement Learning System."
Report from Studies of Artificial Neural Systems, royal Institute of Technology, Sweden.


Zilli, E.~A., ,and M.~E. Hasselmo (2008)
"Modeling the Role of Working Memory and Episodic Memory in Behavioral Tasks."
Hippocampus, Vol. 18(2), pp193-209. 

Johansson, C., P.~Raicevic, and A.~Lansner (2003)
"Reinforcement Learning Based on a Bayesian Confidence Propagating Neural Network."
SAIS-SSLS Joint Workshop, Center for Applied Autonomous Sensor Systems, Orebro, Sweden.


J.~Broekens (2005)
"Internal Simulation of Behavior has an Adaptive Advantage."
Proceedings of the Cognitive Science Conference, pp. 342-347. 



<T-maze by Neural Network>
--------------------------------------------------------------------------------------------------
Sebastian R. and K.~O.~Stanley (2010)
"Indirectly Encoding Neural Plasticity as a Pattern of Local Rules."
Proceedings of the International Conference on Simulation of Adaptive Behavior (From Animals to Animats 11 ). Springer Lecture Notes in Computer Science, Vol. 6226, pp. 533-543.

Blynel, J., Floreano, D. (2003)
"Exploring the T-Maze: Evolving Learning-Like Robot Behaviors using CTRNNs."
Proceedings of the European Workshop on Evolutionary Robotics, pp. 593-604.

Soltoggio, A., J.~A.~Bullinaria, C.~Mattiussi, P.~Durr, and D.~Floreano (2008)
"Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios."
Proceedings of the International Conference on Artificial Life (Alife XI), pp. 569--576.

Soltoggio, A. (2008)
"Neural Plasticity and Minimal Topologies for Reward-Based Learning."
Proceedings of the International Conference on Hybrid Intelligent Systems, pp. 637-642
Internal-Simulation-of-Behavior-has-an-Adaptive-Advantage

Ziemke, T. and M.~Thieme (2002). 
"Neuromodulation of Reactive Sensorimotor Mappings as Short-Term Memory Mechanism in Delayed Response Tasks."
Adaptive Behavior, Vol. 10, pp. 185-19no
9.



acual rat

Ramirez, A.~B., and A.~W.~Ridel (2006(
"Bio-inspired Model of Robot Adaptive Learning and Mapping."
Proceedings of Intrernational Conference on Intelligent robots and System.
pp. 4750-4755.


<Spiking Neurons>
Florean



Emergent-representations-and-reasoning-in-adaptive-agents.-
Reinforcement-Learning-Based-on-a-Bayesian-Confidence-Propagating-Neural-Network

Indirectly-Encoding-Neural-Plasticity-as-a-Pattern-of-Local-Rules

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

Evolutionary-Advantages-of-Neuromodulated-Plasticity-in-Dynamic,-Reward-based-Scenarios

Neuromodulation-of-Reactive-Sensorimotor-Mappings-as-Short-Term-Memory-Mechanism-in-Delayed-Response-Tasks."

Modeling-the-Role-of-Working-Memory-and-Episodic-Memory-in-Behavioral-Tasks."

Reinforcement-Learning-Based-on-a-Bayesian-Confidence-Propagating-Neural-Network

Internal-Simulation-of-Behavior-has-an-Adaptive-Advantage

Bio-inspired-Model-of-Robot-Adaptive-Learning-and-Mapping