Applying a Restricted Mating Policy to Determine State Space Niches Using Immediate and Delayed Reinforcement.
Chris MelhuishTerence C. FogartyPublished in: Evolutionary Computing, AISB Workshop (1994)
Keyphrases
- state space
- reinforcement learning
- optimal policy
- markov decision process
- markov decision problems
- heuristic search
- action space
- continuous state spaces
- markov decision processes
- dynamic programming
- markov chain
- partially observable
- agent receives
- state variables
- function approximation
- reward function
- dynamic systems
- control policies
- continuous time markov process
- infinite horizon
- neural network
- decision problems
- evolutionary algorithm
- search space
- learning algorithm