The utility of reinforcement learning in predation of Batesian mimics.
A. TsoularisPublished in: Int. J. Comput. Aided Eng. Technol. (2009)
Keyphrases
- reinforcement learning
- function approximation
- sequential decision problems
- state space
- utility function
- multi agent
- dynamic programming
- reinforcement learning algorithms
- learning process
- markov decision processes
- model free
- direct policy search
- robotic control
- policy search
- partially observable
- temporal difference
- learning algorithm
- optimal policy
- decision trees
- optimal control
- real robot
- temporal difference learning
- stochastic approximation
- transfer learning
- machine learning