Keyphrases
- reinforcement learning
- function approximation
- robotic control
- control problems
- model free
- database
- function approximators
- reinforcement learning algorithms
- dynamic programming
- state space
- optimal policy
- markov decision processes
- real time
- temporal difference
- optimal control
- multi agent
- computer vision
- genetic algorithm
- image sequences
- learning algorithm
- action space
- neural network
- stochastic approximation
- continuous state
- evolutionary learning
- policy search
- data sets
- direct policy search