Evolutionary Search, Stochastic Policies with Memory, and Reinforcement Learning with Hidden State.
Matthew R. GlickmanKatia P. SycaraPublished in: ICML (2001)
Keyphrases
- hidden state
- evolutionary search
- reinforcement learning
- optimal policy
- partially observable markov decision processes
- fully observable
- evolutionary algorithm
- markov models
- hidden markov models
- fitness function
- markov decision process
- state space
- dynamical systems
- genetic algorithm
- reward function
- search procedure
- finite state
- partially observable
- markov decision problems
- markov decision processes
- decision problems
- search space
- markov model
- genetic programming
- premature convergence
- machine learning
- differential evolution
- maximum entropy
- learning algorithm
- feature selection
- infinite horizon
- evolutionary process
- objective function
- computational complexity
- higher order