Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning.
R. Matthew KretchmarCharles W. AndersonPublished in: IWANN (1) (1999)
Keyphrases
- function approximators
- reinforcement learning
- function approximation
- temporal difference
- reinforcement learning algorithms
- temporal difference learning
- reinforcement learning problems
- temporal difference methods
- continuous state and action spaces
- neural network
- action space
- learning tasks
- learning algorithm
- policy search
- state space
- model free
- real valued
- markov decision processes
- state action
- reinforcement learning methods
- markov decision problems
- continuous state
- multi agent
- machine learning
- evolutionary methods
- evolutionary algorithm
- supervised learning